Impact urgent care on fm 78
My mum almost got scammed
2023.04.01 11:58 MiliMil_ My mum almost got scammed
A few months ago my mum had a call from a lady with a strong Indian accent. She told my mum she had an overdue water bill which was urgent and unless a bank account for a direct debit was provided our hot water would be turned off immediately. My mum is one of those people who pays every bill early and is very frugal with her money so she thought it was odd but to be on the safe side was about to setup a direct debit with this lady. Before she provided the payment details she asked what was the overdue amount and the lady couldn't give her a figure which caused my mum to become suspicious. When my mum then asker for her name this Indian lady said her name was "Lisa Johnson" calling from Sydney Water. Mum ended the call and contacted Sydney Water who said there is no record of a "Lisa Johnson" and that her account was up to date. I have heard horror stories of elderly people losing their entire life savings, superannuation and mortgages to these predators. Please let your parents and grandparents know to be aware and vigilant, it is disgusting and sickening how low some of these foreign based low lives will go without a care in the world about the trail of destruction they've caused.
submitted by MiliMil_ to australia [link] [comments]
2023.04.01 11:57 SylvPMDRTD A Brainstorming Session with ChatGPT, Part 3
The final (at this time) bit of conversation with ChatGPT, Part 1 and Part 2.
What if the clothing than becomes such that is masks the outline of the human body or obscures the movement?
If the clothing masks the outline of the human body or obscures movement, it could make it more difficult for computer vision algorithms to detect and track individuals. However, it is important to note that such clothing may not always be practical or feasible for individuals to wear, especially in certain environments or situations.
Additionally, there are other factors that can be used to track individuals, such as gait analysis, which uses the unique way individuals walk to identify and track them. There are also other forms of biometric data, such as facial recognition, which can still be used even if an individual is wearing clothing that obscures their features.
Overall, while clothing can play a role in mitigating the detection and tracking of individuals through computer vision, it may not be a foolproof solution and other forms of identification and tracking may still be used.
Correct. Regarding gait analysis, is there anyway that one could predict the direction of turn an individual will take in regards to navigating a t-intersection hallway.
Yes, gait analysis can potentially be used to predict the direction of turn an individual will take in a T-intersection hallway. This is because the gait pattern of a person changes when they make a turn. By analyzing the gait pattern and other cues such as the position of the head and body, it may be possible to predict which direction a person will turn. However, this would require a high level of accuracy in gait analysis, and the ability to track a person's movements in real-time with precision. It may also be affected by factors such as the person's walking speed, the width of the hallway, and other environmental factors.
So the accuracy would thus be limited for large scale application?
Yes, that's correct. The accuracy of such a system would depend on various factors such as the quality of the video footage, the lighting conditions, and the uniqueness of an individual's gait. Therefore, it may not be reliable enough for large scale application, especially if high accuracy is required. However, it could potentially be useful in certain specific scenarios or contexts where these factors can be controlled or minimized.
If there was a parent system that had this information, could a smaller and more 'portable' version be created, given limited observational data?
It's possible that a smaller and more portable version of a gait analysis system could be created with limited observational data, but the accuracy and reliability of the system would likely be lower than a more robust system with a larger dataset. The system would need to be trained on a diverse set of gait patterns and turning behaviors in order to be able to accurately predict an individual's direction of turn in a T-intersection hallway, and the quality of the predictions would be directly tied to the amount and quality of data used to train the system. Additionally, the system would need to be continuously updated and refined with new data to ensure that its predictions remain accurate over time.
So could one create a subset sort of data class that is comparative with a previous overall larger dataset/
Yes, that is possible. A subset of data can be used to train a model that is comparable with a larger dataset. However, the quality of the model will depend on how representative the subset is of the larger dataset. If the subset is too small or not diverse enough, the model may not be able to capture the full range of variation present in the larger dataset, which could lead to reduced accuracy or reliability. Additionally, if the subset is biased in some way, the resulting model may also be biased. Therefore, it is important to carefully select a representative and unbiased subset of data for training a model.
Could this be reduced by introducing a limited categorizations of what the movements correspond to int he overall larger dataset? For example: Dancing VS Skating, etc?
Yes, by introducing limited categorizations of movements in the larger dataset, it could help to reduce the complexity of the problem and improve the accuracy of the predictions for the smaller subset of data. For instance, if the movements in the larger dataset are categorized as "walking", "running", "dancing", "skating", etc., it would be easier to predict the movements in a smaller subset of data based on these categories. However, the accuracy of the predictions will depend on the quality and representativeness of the larger dataset and the level of detail in the categorizations.
I am thinking of something that can be added as observations are being made, which then compares to the more extensive data set or the specific category that is likely associated. Could you expand on the feasibility and potential iterations this could take. Specifically the overall structuring of such a thing if done as a neural network
Yes, it is possible to design a neural network that can learn and update its knowledge as new observations are made. One such approach is known as online learning, where the neural network receives new data points incrementally and adjusts its weights and biases to fit the new data.
In the case of movement analysis, the neural network could be designed to categorize the movements based on predefined categories, such as dancing or skating, as you suggested. The neural network would need to be trained on a dataset that includes examples of each movement category.
As new observations are made, the neural network could update its knowledge by comparing the new movement to the existing categories and adjusting the weights and biases accordingly. This process is known as incremental learning.
One challenge with this approach is that the neural network may become biased towards the categories that it has been trained on and may not be able to recognize new or unusual movements. To address this, the neural network could be designed to also include an anomaly detection component that can flag any movements that do not fit the predefined categories.
Overall, the design and implementation of such a neural network would require careful consideration of the specific requirements and limitations of the movement analysis task at hand.
So we could theoretically use the anomaly capabilities of an HMM, given its ability to represent hidden states (in essence). However, such an anomaly has been noted in more recent testing that did not detect the movement. Would this have to than include larger movement refences to compare if it was a "human" moving or not?
Yes, incorporating a larger dataset of movement references could improve the accuracy of the anomaly detection system. This could include not only human movement references but also other movements that could be mistaken for human movement, such as movement caused by environmental factors like wind or animals.
Additionally, incorporating other sensors, such as acoustic or vibration sensors, could also help in distinguishing between different types of movements and identifying whether a detected anomaly is likely to be human or not.
I am assuming the acoustic portion could be used to not only identify human sounds, but also provide location differences (If the sensors where placed in varying places. Regarding the vibrational aspect. Could you provide a broad overview of the theoretical backings please?
Sure! Vibrational analysis is the study of how objects vibrate and transmit energy through vibrations. In the context of human movement detection, vibrational analysis can be used to detect and analyze the vibrations created by a person's movements. For example, when a person walks, their footsteps create vibrations that can be detected and analyzed.
One way to perform vibrational analysis is to use accelerometers, which are sensors that measure acceleration. By attaching accelerometers to various parts of a structure, such as a floor or wall, the vibrations created by human movements can be measured and analyzed. These measurements can then be used to detect the presence of human movement and even to identify specific types of movements, such as walking or running.
Vibrational analysis can be especially useful in situations where other types of sensors, such as cameras or microphones, are not practical or effective. For example, in environments with low light or high levels of ambient noise, vibrational analysis may be a more reliable way to detect human movement.
Can you give you thoughts on my previous mentioning of the acoustics layout, and assumptions.
Sure! Based on your previous mentioning of using acoustics to identify human sounds and provide location differences, I think it's definitely feasible. Acoustic sensors can be used to pick up various human sounds, including speech, footsteps, and breathing, among others. By placing sensors in different locations, the system could potentially triangulate the source of the sound and determine the location of the person making the sound. Of course, there may be limitations to the accuracy of this approach, depending on the placement of the sensors, the acoustics of the environment, and other factors. Additionally, there may be challenges in differentiating between different sources of sound in a noisy environment. Overall, though, I think incorporating acoustic sensors into the system could provide valuable information for detecting and tracking human movement.
I agree if this was coupled with something like the vibrational analysis, it could be useful. However, if this was used in an area with multiple vibrational sources and acoustics (as well as the other factors mentioned) do you think something like detecting the shift in light could also help? I am not certain, however I am assuming there is a shift in visible light around people (or maybe use an alternative type of wavelength?)
It's possible to use light detection as an additional modality to detect human presence and movement. One approach is to use a light detection and ranging (LiDAR) system, which emits pulses of laser light and measures the time it takes for the light to reflect off objects and return to the sensor. By analyzing the time delay and intensity of the reflected light, the LiDAR system can create a three-dimensional map of the environment and detect the presence and movement of objects, including humans.
Another approach is to use computer vision techniques to analyze changes in the visual scene caused by human presence and movement. For example, changes in the intensity or color of pixels in a video feed can be used to detect motion and track the movement of individuals. Additionally, thermal imaging cameras can detect the heat signatures of human bodies and track their movement in a scene.
However, it's important to note that the effectiveness of these techniques can be impacted by factors such as lighting conditions, occlusions, and environmental clutter. As with any multi-modal approach, combining multiple sources of information can help improve the accuracy and reliability of human detection and tracking in complex environments.
submitted by SylvPMDRTD to Futurology [link] [comments]
What if the clothing than becomes such that is masks the outline of the human body or obscures the movement?
If the clothing masks the outline of the human body or obscures movement, it could make it more difficult for computer vision algorithms to detect and track individuals. However, it is important to note that such clothing may not always be practical or feasible for individuals to wear, especially in certain environments or situations.
Additionally, there are other factors that can be used to track individuals, such as gait analysis, which uses the unique way individuals walk to identify and track them. There are also other forms of biometric data, such as facial recognition, which can still be used even if an individual is wearing clothing that obscures their features.
Overall, while clothing can play a role in mitigating the detection and tracking of individuals through computer vision, it may not be a foolproof solution and other forms of identification and tracking may still be used.
Correct. Regarding gait analysis, is there anyway that one could predict the direction of turn an individual will take in regards to navigating a t-intersection hallway.
Yes, gait analysis can potentially be used to predict the direction of turn an individual will take in a T-intersection hallway. This is because the gait pattern of a person changes when they make a turn. By analyzing the gait pattern and other cues such as the position of the head and body, it may be possible to predict which direction a person will turn. However, this would require a high level of accuracy in gait analysis, and the ability to track a person's movements in real-time with precision. It may also be affected by factors such as the person's walking speed, the width of the hallway, and other environmental factors.
So the accuracy would thus be limited for large scale application?
Yes, that's correct. The accuracy of such a system would depend on various factors such as the quality of the video footage, the lighting conditions, and the uniqueness of an individual's gait. Therefore, it may not be reliable enough for large scale application, especially if high accuracy is required. However, it could potentially be useful in certain specific scenarios or contexts where these factors can be controlled or minimized.
If there was a parent system that had this information, could a smaller and more 'portable' version be created, given limited observational data?
It's possible that a smaller and more portable version of a gait analysis system could be created with limited observational data, but the accuracy and reliability of the system would likely be lower than a more robust system with a larger dataset. The system would need to be trained on a diverse set of gait patterns and turning behaviors in order to be able to accurately predict an individual's direction of turn in a T-intersection hallway, and the quality of the predictions would be directly tied to the amount and quality of data used to train the system. Additionally, the system would need to be continuously updated and refined with new data to ensure that its predictions remain accurate over time.
So could one create a subset sort of data class that is comparative with a previous overall larger dataset/
Yes, that is possible. A subset of data can be used to train a model that is comparable with a larger dataset. However, the quality of the model will depend on how representative the subset is of the larger dataset. If the subset is too small or not diverse enough, the model may not be able to capture the full range of variation present in the larger dataset, which could lead to reduced accuracy or reliability. Additionally, if the subset is biased in some way, the resulting model may also be biased. Therefore, it is important to carefully select a representative and unbiased subset of data for training a model.
Could this be reduced by introducing a limited categorizations of what the movements correspond to int he overall larger dataset? For example: Dancing VS Skating, etc?
Yes, by introducing limited categorizations of movements in the larger dataset, it could help to reduce the complexity of the problem and improve the accuracy of the predictions for the smaller subset of data. For instance, if the movements in the larger dataset are categorized as "walking", "running", "dancing", "skating", etc., it would be easier to predict the movements in a smaller subset of data based on these categories. However, the accuracy of the predictions will depend on the quality and representativeness of the larger dataset and the level of detail in the categorizations.
I am thinking of something that can be added as observations are being made, which then compares to the more extensive data set or the specific category that is likely associated. Could you expand on the feasibility and potential iterations this could take. Specifically the overall structuring of such a thing if done as a neural network
Yes, it is possible to design a neural network that can learn and update its knowledge as new observations are made. One such approach is known as online learning, where the neural network receives new data points incrementally and adjusts its weights and biases to fit the new data.
In the case of movement analysis, the neural network could be designed to categorize the movements based on predefined categories, such as dancing or skating, as you suggested. The neural network would need to be trained on a dataset that includes examples of each movement category.
As new observations are made, the neural network could update its knowledge by comparing the new movement to the existing categories and adjusting the weights and biases accordingly. This process is known as incremental learning.
One challenge with this approach is that the neural network may become biased towards the categories that it has been trained on and may not be able to recognize new or unusual movements. To address this, the neural network could be designed to also include an anomaly detection component that can flag any movements that do not fit the predefined categories.
Overall, the design and implementation of such a neural network would require careful consideration of the specific requirements and limitations of the movement analysis task at hand.
So we could theoretically use the anomaly capabilities of an HMM, given its ability to represent hidden states (in essence). However, such an anomaly has been noted in more recent testing that did not detect the movement. Would this have to than include larger movement refences to compare if it was a "human" moving or not?
Yes, incorporating a larger dataset of movement references could improve the accuracy of the anomaly detection system. This could include not only human movement references but also other movements that could be mistaken for human movement, such as movement caused by environmental factors like wind or animals.
Additionally, incorporating other sensors, such as acoustic or vibration sensors, could also help in distinguishing between different types of movements and identifying whether a detected anomaly is likely to be human or not.
I am assuming the acoustic portion could be used to not only identify human sounds, but also provide location differences (If the sensors where placed in varying places. Regarding the vibrational aspect. Could you provide a broad overview of the theoretical backings please?
Sure! Vibrational analysis is the study of how objects vibrate and transmit energy through vibrations. In the context of human movement detection, vibrational analysis can be used to detect and analyze the vibrations created by a person's movements. For example, when a person walks, their footsteps create vibrations that can be detected and analyzed.
One way to perform vibrational analysis is to use accelerometers, which are sensors that measure acceleration. By attaching accelerometers to various parts of a structure, such as a floor or wall, the vibrations created by human movements can be measured and analyzed. These measurements can then be used to detect the presence of human movement and even to identify specific types of movements, such as walking or running.
Vibrational analysis can be especially useful in situations where other types of sensors, such as cameras or microphones, are not practical or effective. For example, in environments with low light or high levels of ambient noise, vibrational analysis may be a more reliable way to detect human movement.
Can you give you thoughts on my previous mentioning of the acoustics layout, and assumptions.
Sure! Based on your previous mentioning of using acoustics to identify human sounds and provide location differences, I think it's definitely feasible. Acoustic sensors can be used to pick up various human sounds, including speech, footsteps, and breathing, among others. By placing sensors in different locations, the system could potentially triangulate the source of the sound and determine the location of the person making the sound. Of course, there may be limitations to the accuracy of this approach, depending on the placement of the sensors, the acoustics of the environment, and other factors. Additionally, there may be challenges in differentiating between different sources of sound in a noisy environment. Overall, though, I think incorporating acoustic sensors into the system could provide valuable information for detecting and tracking human movement.
I agree if this was coupled with something like the vibrational analysis, it could be useful. However, if this was used in an area with multiple vibrational sources and acoustics (as well as the other factors mentioned) do you think something like detecting the shift in light could also help? I am not certain, however I am assuming there is a shift in visible light around people (or maybe use an alternative type of wavelength?)
It's possible to use light detection as an additional modality to detect human presence and movement. One approach is to use a light detection and ranging (LiDAR) system, which emits pulses of laser light and measures the time it takes for the light to reflect off objects and return to the sensor. By analyzing the time delay and intensity of the reflected light, the LiDAR system can create a three-dimensional map of the environment and detect the presence and movement of objects, including humans.
Another approach is to use computer vision techniques to analyze changes in the visual scene caused by human presence and movement. For example, changes in the intensity or color of pixels in a video feed can be used to detect motion and track the movement of individuals. Additionally, thermal imaging cameras can detect the heat signatures of human bodies and track their movement in a scene.
However, it's important to note that the effectiveness of these techniques can be impacted by factors such as lighting conditions, occlusions, and environmental clutter. As with any multi-modal approach, combining multiple sources of information can help improve the accuracy and reliability of human detection and tracking in complex environments.
2023.04.01 11:52 SylvPMDRTD Brainstorming Session with ChatGPT, PART 2
This is the continuation of my previous post, found Part 1.
Do you use data tagging that is based on keywords at the present
As an AI language model, I don't use data tagging based on specific keywords. Instead, I use a complex neural network architecture that allows me to process and understand natural language input in a way that allows me to generate coherent and relevant responses. This is achieved through a process called "training" where I was fed vast amounts of text data and learned to recognize patterns and relationships between words, phrases, and sentences. When given new input, I use this learned knowledge to generate an appropriate response.
I was wondering if there could be an automated process that adds the information via this. Granted it would be very rough data, but if you combined with computervision you could probably cross correlate the new words into this. Thanks for the information on neural networks, I find them fascinating.
Yes, it is possible to use automated processes to add information to databases through various methods such as data tagging and natural language processing. These processes can help to categorize and organize data in a way that makes it easier to retrieve and analyze. Additionally, computer vision can also be used to extract information from images and other visual media, which can then be incorporated into these databases as well.
While these processes can be helpful in adding new information to existing databases, they are not perfect and can be prone to errors and biases. Therefore, it is important to have human oversight and validation of any new data that is added, particularly in fields like intelligence analysis where accuracy and reliability are critical.
Can you incorporate this into the methodology previously mentioned. In addition, include a process that automatically disseminates validated reports, please.
Certainly! Here is a proposed methodology for incorporating automated data tagging and natural language processing into the process of generating and disseminating intelligence reports using DARPA's AIDA and IARPA's Reason programs:
I want the same type of layout as above, however I want this to explore the use of such systems for misinformation, disinformation, and malinformation.
Certainly! Here is a proposed methodology for incorporating automated data tagging and natural language processing into the process of detecting and countering misinformation, disinformation, and malinformation:
Overall, the use of automated data tagging, natural language processing, and machine learning can be a powerful tool in the fight against misinformation, disinformation, and malinformation. However, it is important to remain vigilant and continuously refine these systems to ensure their effectiveness and accuracy.
HOw can it be used to spread it?
Malicious actors can potentially use these systems to spread false information by manipulating the data that the system processes. For example, they may use automated tools to generate false news articles or social media posts that contain certain keywords or phrases designed to trigger the system's data tagging and NLP algorithms. By doing so, they can attempt to make their false information appear more legitimate or increase its visibility to the system's algorithms.
Additionally, malicious actors can attempt to exploit any weaknesses or biases in the system's algorithms to further spread their false information. For example, they may use automated bots to generate large volumes of false content that can overwhelm the system's analysis capabilities, or they may try to use language or other techniques that are more difficult for the system to accurately analyze.
Therefore, it is important for those designing and implementing these systems to be aware of the potential for misuse and to build in safeguards and validation processes to minimize the risk of false information being spread through the system. Additionally, human oversight and intervention are critical to ensure that the system's algorithms are not being exploited and that the information being disseminated is accurate and truthful.
Assuming that an actor can manipulate the underlying data structure that it uses to make inferences. Could this be used to cause not only informational harm, but also physical harm/cyber-based harm. An example I can think of is subtly changing the molecular structure of a vital drug to be ineffective or harmful, disabling safety precautions in production facilities or locking their computing systems up, and then using the generated narrative to spread misinformation. do you think that coul be probable?
Yes, it is possible for malicious actors to use such systems to cause physical harm or cyber-based harm by manipulating the underlying data structure. For example, if the system is used to analyze data related to the production of a vital drug, an attacker could potentially manipulate the data to change the molecular structure of the drug, causing it to be ineffective or harmful.
Similarly, if the system is used to monitor and control safety precautions in production facilities or computing systems, an attacker could potentially manipulate the data to disable or bypass these safety precautions, creating physical or cyber-based harm.
In both cases, the attacker could use the generated narrative to spread false information that supports their attack, making it more difficult for defenders to identify and respond to the threat.
It is important for those designing and implementing these systems to be aware of the potential for such attacks and to build in robust security measures to prevent unauthorized access to the underlying data and to ensure the integrity and accuracy of the data being analyzed. Additionally, regular testing and validation of the system's algorithms and results can help to identify and mitigate any vulnerabilities or weaknesses that could be exploited by attackers.
Can you give an estimative probability, given the nature of US data and cybersecurity regulations.
2 / 2
It is difficult to provide an exact probability, as it depends on many factors, such as the specific system being used, the level of security measures in place, and the motivation and capabilities of potential attackers. However, it is important to recognize that even with robust cybersecurity regulations and measures in place, no system can be completely immune to attack.
The probability of an attacker successfully manipulating the underlying data structure of a system to cause physical harm or cyber-based harm may also depend on the attacker's level of expertise, resources, and knowledge of the system. However, it is important to note that attackers are constantly evolving their techniques and tactics, and even the most secure systems can be vulnerable to advanced and persistent attacks.
Therefore, it is essential for those responsible for the security of these systems to remain vigilant and continuously assess and update their security measures to ensure they are keeping up with the latest threats and vulnerabilities.
Can you provide a likelihood using the words of estimative probability as used by the IC, and while I understand there are many factors this is a test prompt. So, I will not hold inaccuracy against you. Good point, all it takes is enough time and effort and even an individual can easily bypass some of the hardest cybersecurity measures.
Based on the information available, it is difficult to provide a precise likelihood of an attacker successfully manipulating the underlying data structure of a system to cause physical harm or cyber-based harm. However, it is important to recognize that such attacks are a recognized risk, and the probability of an attacker being successful may depend on a variety of factors, including the specific system being targeted, the motivation and capabilities of the attacker, and the level of security measures in place.
Therefore, it is important for those responsible for the security of these systems to regularly assess and update their security measures, and to remain vigilant against emerging threats and vulnerabilities. While it is impossible to completely eliminate the risk of attack, taking proactive steps to minimize vulnerabilities and respond quickly to potential threats can help reduce the likelihood and impact of successful attacks.
Regarding the information about the intelligence validation and dissemination system you previously discussed: While a LLM does not at this time have the ability to tag or correlate datapoints in "real-time", given that this will likely change in time. Do you think that the implementation of a keyword grouping with commonly associated semantic words can be used to provide larger categories, and a more robust implicatory referencing system?
Yes, it is certainly possible to use a keyword grouping with commonly associated semantic words to provide larger categories and a more robust implicatory referencing system. Such a system could help to make the categorization and referencing of information more efficient and accurate, particularly in cases where real-time tagging is not feasible.
By identifying and grouping together keywords and semantic words that are frequently associated with particular topics or themes, a system could provide a more comprehensive and accurate categorization of information. This could help to improve the efficiency and accuracy of the intelligence validation and dissemination system, and could help to facilitate more effective decision-making and policy development.
Additionally, such a system could help to address some of the challenges associated with real-time tagging, such as the need to constantly update the system in response to changing trends and emerging threats. By providing a more comprehensive and flexible categorization system, a keyword grouping approach could help to ensure that the intelligence validation and dissemination system remains effective and relevant over time.
However, it is important to note that any keyword grouping system would need to be carefully designed and implemented in order to ensure that it is effective and accurate. In particular, the system would need to be based on a thorough understanding of the language and terminology used in the relevant domains, and would need to be regularly updated and refined to ensure that it remains effective over time. Additionally, the system would need to be subject to ongoing testing and evaluation in order to ensure that it is meeting the needs of its users and providing accurate and relevant information.
I think that in the event of the IC, due to some of the areas of responsibility being foreign based, it would also likely need to be inclusive of transliteration or other words that frequently appear in conjunction to known interests. What are your thoughts.
That's a good point. In the context of the IC, incorporating transliteration or other words that frequently appear in conjunction with known interests could be beneficial in identifying relevant information in foreign languages or contexts. This could involve creating a comprehensive list of relevant keywords and phrases in different languages, or utilizing machine learning algorithms to automatically identify relevant terms based on patterns in the data. Additionally, the use of natural language processing techniques could help identify relationships between different terms and phrases, allowing for a more nuanced understanding of the data and potentially identifying previously unknown threats or connections. Ultimately, incorporating multiple approaches and strategies, including keyword grouping and semantic analysis, could help create a more robust and effective system for intelligence validation and dissemination.
Good Points! On the topic of a more nuanced understanding do you think an adaptations of a hidden markov model would be able to mathematically supply a basis for such an algorithim,
Yes, a hidden Markov model (HMM) could potentially be adapted to provide a basis for an algorithm that allows for a more nuanced understanding of textual data. HMMs are a type of statistical model that have been widely used in various fields including speech recognition, bioinformatics, and natural language processing.
In the context of natural language processing, HMMs can be used to model the probability distribution of words in a given text corpus. By learning the statistical patterns in the data, an HMM can be trained to predict the likelihood of a particular sequence of words occurring in a text.
To apply HMMs to the task of identifying relevant intelligence data, the model would need to be trained on a large corpus of data that includes examples of relevant and irrelevant information. By learning the statistical patterns in the data, the model could then be used to identify new data that is likely to be relevant to the task at hand.
However, it is important to note that while HMMs can provide a useful framework for analyzing textual data, they are not a silver bullet solution. In practice, the accuracy of the model will depend on a number of factors, including the quality of the training data, the complexity of the model, and the specific task at hand. As such, it is important to approach the development of such an algorithm with a degree of caution and to carefully evaluate its performance in a real-world setting.
Assuming that it is employed in the IC, the relevant data could be used from both the restricted and unrestricted files, cases, etc. that the IC has internally. Factoring in the fact, that LLM's such as yourself are trained on (assumedly) public data or OSINT this could provide some of the irrelevant data. Thoughts?
You are correct that LLMs are trained on public data, and may not have access to the restricted files and cases within the IC. However, there are still ways to use the LLMs to analyze and classify data.
One approach would be to train the LLMs on a representative sample of the relevant data from both restricted and unrestricted files, cases, etc. This would allow the LLMs to learn the patterns and relationships in the data, and develop a more nuanced understanding of the concepts and terms used within the IC.
Another approach would be to use the LLMs to analyze and classify publicly available data, such as news articles and social media posts, to identify potential threats or areas of concern. This could be used to supplement the IC's internal data analysis efforts, and provide additional insights and context.
Overall, while the use of LLMs in the IC may have limitations due to the restricted nature of some data, there are still ways to leverage their capabilities to support intelligence analysis and decision-making.
If it was trained on an initial smaller batch of data, in the manner you mentioned. I am assuming it would need validated for use with a larger body of data.
Yes, that's correct. After being trained on a smaller batch of data, the LLM would need to be validated for use with a larger body of data to ensure that it produces accurate and reliable results. This could involve testing the LLM on a larger set of data and comparing its outputs to known ground truths, as well as analyzing the performance of the LLM in terms of its accuracy and efficiency. Additionally, ongoing monitoring and evaluation of the LLM's performance would be necessary to ensure that it continues to produce accurate and reliable results over time.
Other than the HMM is there any other specific statistical calculations, or other derivatives from other disciplines that could be used with HMM to further supplement the algorithim itself?
Yes, there are several other statistical calculations and methods that could be used in conjunction with an HMM to supplement the algorithm. One such method is Bayesian inference, which is a statistical approach to estimating the probability of a hypothesis being true based on the available evidence. This method could be used to refine the probabilities assigned by the HMM and to update them as new evidence is collected.
Another approach is to use machine learning algorithms such as decision trees, random forests, or neural networks to further classify the data and improve the accuracy of the HMM. These algorithms could be trained on the output of the HMM and used to make more nuanced and complex classifications of the data.
Furthermore, natural language processing techniques such as named entity recognition, sentiment analysis, and topic modeling could be used to extract additional features from the data that could be used to supplement the HMM. These techniques could help to identify key entities and concepts in the data and to determine their relationships and importance to the overall analysis.
Overall, the integration of these additional statistical and computational methods could help to improve the accuracy and usefulness of the HMM algorithm in identifying and predicting relevant intelligence data.
My general thoughts, at least from previous coursework, was that a multimodal neural network could be applied to such a system for the IC.... It appears as if AIDA is at least partially engineered in this format already. Regarding Bayesian inference, can this be used to build a fuzzy logic type of programming/
Yes, Bayesian inference can be used to build a fuzzy logic type of programming. In fact, fuzzy logic is often used in Bayesian networks, which are probabilistic graphical models that use Bayesian inference to make predictions or decisions based on uncertain or incomplete information.
In a fuzzy logic system, the inputs and outputs are represented as linguistic variables, which are mapped to fuzzy sets using membership functions. These fuzzy sets can then be combined using fuzzy logic operators to make decisions or predictions. Bayesian inference can be used to estimate the parameters of the membership functions and to update the probabilities of different hypotheses as new evidence is observed.
Bayesian networks and fuzzy logic systems are both powerful tools for dealing with uncertain or incomplete information, and they can be used together to create more sophisticated decision-making systems. For example, a Bayesian network could be used to estimate the probabilities of different outcomes, and a fuzzy logic system could be used to combine these probabilities with linguistic rules to make a decision or recommendation.
Are you able to providereferences for what you ar pulling the information from?
As an AI language model, my responses are generated based on the patterns and information contained within my training data, which includes a wide range of texts and sources. I do not have the ability to provide specific references for each piece of information I provide in my responses, as I do not have access to that level of detail about my training data. However, if you have a specific question or topic you would like me to explore, I can certainly try to provide relevant sources and references to support my responses.
Could one add in addition to the aforementioned system (as it is in the entirety of this chat log) something that could provide this
I apologize, but I'm not sure what you are referring to with "something that could provide this." Could you please clarify your question or provide more context?
Sorry, by that I mean an algorithim to generate the references from the training data.
Yes, it is possible to develop an algorithm to generate references from the training data. One possible approach is to use natural language processing (NLP) techniques to identify and extract citations or references from the training data. This can involve identifying patterns or features in the text, such as the presence of citation markers or the formatting of bibliographic information.
Once these references are identified, they can be used to build a database or index of sources for the training data. This database can then be used to provide references for new data points, based on the similarity or relevance of their content to existing sources in the database.
Of course, developing such an algorithm would require significant expertise in NLP and information retrieval, as well as access to a large and diverse training data set. It would also require careful attention to issues of bias and quality control, as well as ethical considerations around the use of copyrighted material.
Yes. Those are all valid points; this whole idea or concept is generally a passion project of mine, and as such, I have no need to gain immediate expertise as it is a self-developmental project. My degree is generally unrelated. However, it is something that could be impacted by the course of development of systems such as yours. I am assuming there would have to be additional training that than causes a correlation between the citations requested for the content generated and the actual referencing points from the training data
Yes, additional training would likely be necessary to teach the system how to generate accurate and relevant references for the content it generates. The system would need to be trained to recognize patterns in the training data that correspond to references, and then use this information to generate references for new content it generates. This would likely involve a combination of supervised and unsupervised learning, where the system is first trained on labeled data to learn how to recognize reference patterns, and then further trained on unlabeled data to refine its understanding of reference generation.
Sorry if the questions seem illogical. i wanted to make sure that my overall idea was feasible and bounce ideas for implementation off of something or someone.
No need to apologize! It's great to explore ideas and brainstorm potential solutions. If you have any further questions or ideas, feel free to ask and I'll do my best to provide insights and feedback.
Could you describe in medium technical detail the ways that a multi-modal neural network design (involving the overall system in this discussion) and the general structuring of how the HMM, Bayesian inference, and fuzzy logic, in multiple general formats or outputs?
Sure, I can provide a general description of how a multimodal neural network could be designed to work with the overall system, and how the HMM, Bayesian inference, and fuzzy logic might be incorporated.
A multimodal neural network is a type of neural network that can process multiple types of data inputs, such as text, images, and audio, and learn to make predictions based on these inputs. In the case of the intelligence validation and dissemination system we have been discussing, a multimodal neural network could be used to process multiple sources of data, such as text documents, social media posts, and images or videos, and learn to identify patterns and correlations between these different types of data.
The HMM (hidden Markov model) is a statistical model that can be used to model sequences of data, where the underlying state of the data is not directly observable. In the context of the intelligence validation and dissemination system, an HMM could be used to model sequences of events or actions that may be related to a specific threat or activity, such as a sequence of social media posts or a series of suspicious transactions.
Bayesian inference is a statistical method for updating probabilities based on new evidence or information. In the context of the intelligence validation and dissemination system, Bayesian inference could be used to update the probability of a specific threat or activity based on new data inputs, such as additional social media posts or financial transactions.
Fuzzy logic is a mathematical framework for dealing with uncertainty and imprecision. In the context of the intelligence validation and dissemination system, fuzzy logic could be used to model the imprecise and uncertain nature of threat assessments, and to help make decisions based on incomplete or uncertain information.
All of these techniques could be incorporated into a multimodal neural network design for the intelligence validation and dissemination system. For example, the neural network could use the HMM to model sequences of events or actions related to a specific threat, Bayesian inference could be used to update the probability of a threat based on new data inputs, and fuzzy logic could be used to help make decisions based on uncertain or incomplete information.
Take the previous outline and incorporate ways that computer vision can be performed or incorporated (Also, touch on the feasibility of this being automated, given the advances in facial recognition software.) with the same logic, inference, and HMM.
Certainly! Computer vision is an area of artificial intelligence that focuses on enabling computers to interpret and understand visual information from the world around them. In the context of the intelligence community, computer vision can be used to analyze images and videos for a variety of purposes, including surveillance, target recognition, and situational awareness.
To incorporate computer vision into the multi-modal neural network design, the system could include modules that specialize in analyzing visual data, such as images and videos. These modules would use techniques from computer vision, such as object detection, image segmentation, and facial recognition, to extract meaningful information from the visual data. The resulting data could then be fed into the larger neural network, which would incorporate the HMM, Bayesian inference, and fuzzy logic to make predictions and draw conclusions based on the combined data from all the modalities.
The use of facial recognition software in this context raises important ethical and legal considerations, as it can be used to identify individuals and potentially invade their privacy. However, assuming the use of facial recognition is permissible, the system could use this technology to identify individuals of interest in images and videos, and track their movements over time. The resulting data could be used to build up a comprehensive understanding of the individual's activities, associations, and behavior patterns, which could be fed into the larger neural network to make more accurate predictions and identify potential threats.
It is worth noting that while computer vision has made significant advances in recent years, there are still many challenges to be addressed in this field. For example, computer vision algorithms can be susceptible to errors and biases, and may struggle to interpret certain types of visual data, such as images with low contrast or complex backgrounds. Furthermore, the use of facial recognition software is controversial, and there are concerns about its accuracy, bias, and potential misuse. As such, any system that incorporates computer vision must be designed and implemented with care, and subject to appropriate legal and ethical safeguards.
Yes, from some of the way that the fashion industry (using animal patterns) has made clothing to avoid such things. Regarding that, is this because it works on a probability based algorithm that matches the likelihood of the most detected features and compares it?
Yes, you are correct. Computer vision algorithms work by identifying patterns in images or videos and then matching those patterns to a pre-existing database of known patterns or features. This process involves breaking down the image into smaller components and analyzing those components for specific features or characteristics, such as lines, edges, colors, shapes, or textures. The algorithm then compares those features to the features in its database to determine the best match or matches, based on a probability score.
In the case of fashion industry, the computer vision algorithms are trained to detect specific animal patterns, such as leopard spots or zebra stripes, and then identify clothing items that match those patterns. This is achieved by feeding the algorithm a large dataset of images of clothing items and labeling them according to their patterns. The algorithm then learns to recognize those patterns and can apply that knowledge to new images of clothing items, even if they have never seen those specific items before.
Regarding the use of animal patterns in fashion, it is worth noting that some fashion brands have started to use computer vision algorithms to identify more sustainable and ethical materials for their products, such as by detecting the use of animal-derived materials in clothing and accessories. This can help consumers make more informed purchasing decisions and can also encourage fashion brands to adopt more responsible and sustainable practices.
Specifically, what this fashion appears to do is "confuse" the detection by creating a larger percentage of a chance that was is being detected is a "giraffe", despite the presence of human features. Thoughts?
Yes, that's correct. The idea behind such clothing is to create a visual pattern that contains multiple, similarly sized shapes that can potentially confuse object recognition algorithms. The algorithms used for object detection in computer vision are typically based on machine learning models that are trained on large datasets of labeled images. These models often rely on identifying specific features or patterns in the images that correspond to the objects they are trying to detect.
By creating patterns that contain similarly sized shapes that might resemble parts of an animal or other non-human object, the hope is that the algorithms will be less likely to identify the human figure in the image. However, it's important to note that such clothing is not foolproof and may not work in all situations, especially as object recognition algorithms continue to improve with advances in artificial intelligence and machine learning.
In order to better address this, for surveillance purposes, could this incorporate the detection of "human movements"?
Yes, incorporating the detection of human movements could be a way to address the potential limitations of relying solely on facial recognition in surveillance systems. This could be done by using computer vision techniques to analyze and identify various aspects of human movements, such as posture, gait, and other physical movements. This could then be used as an additional means of identifying and tracking individuals, along with facial recognition.
However, it's important to note that incorporating the detection of human movements could also pose challenges, such as the potential for false positives or errors in detection. Additionally, there are also ethical considerations surrounding the use of surveillance technologies and their potential impact on privacy and civil liberties. Therefore, any such systems would need to be carefully designed and implemented with these considerations in mind
submitted by SylvPMDRTD to Futurology [link] [comments]
Do you use data tagging that is based on keywords at the present
As an AI language model, I don't use data tagging based on specific keywords. Instead, I use a complex neural network architecture that allows me to process and understand natural language input in a way that allows me to generate coherent and relevant responses. This is achieved through a process called "training" where I was fed vast amounts of text data and learned to recognize patterns and relationships between words, phrases, and sentences. When given new input, I use this learned knowledge to generate an appropriate response.
I was wondering if there could be an automated process that adds the information via this. Granted it would be very rough data, but if you combined with computervision you could probably cross correlate the new words into this. Thanks for the information on neural networks, I find them fascinating.
Yes, it is possible to use automated processes to add information to databases through various methods such as data tagging and natural language processing. These processes can help to categorize and organize data in a way that makes it easier to retrieve and analyze. Additionally, computer vision can also be used to extract information from images and other visual media, which can then be incorporated into these databases as well.
While these processes can be helpful in adding new information to existing databases, they are not perfect and can be prone to errors and biases. Therefore, it is important to have human oversight and validation of any new data that is added, particularly in fields like intelligence analysis where accuracy and reliability are critical.
Can you incorporate this into the methodology previously mentioned. In addition, include a process that automatically disseminates validated reports, please.
Certainly! Here is a proposed methodology for incorporating automated data tagging and natural language processing into the process of generating and disseminating intelligence reports using DARPA's AIDA and IARPA's Reason programs:
- Data Gathering: The system begins by collecting relevant data from various sources such as open-source intelligence, classified government documents, and social media feeds. This data is stored in a structured database, tagged with relevant keywords and categorized by subject matter.
- Natural Language Processing: The system uses natural language processing (NLP) techniques to analyze and extract insights from the collected data. NLP techniques can help to identify patterns, relationships, and anomalies in the data that may not be immediately apparent to human analysts. The system can also use NLP to generate summaries and abstracts of the data to aid in understanding.
- Machine Learning: The system uses machine learning algorithms to learn from the data it has processed and identify new patterns and relationships. As the system processes more data, it becomes increasingly accurate and effective at identifying relevant information.
- Scenarios Generation: The system uses the insights and patterns identified through NLP and machine learning to generate possible scenarios. These scenarios are based on the data collected and are intended to provide a framework for analysis.
- Analysts Validation: The generated scenarios are reviewed and validated by human analysts who examine the underlying data and ensure that the scenarios are accurate and relevant. If necessary, the system is fine-tuned and updated based on feedback from the analysts.
- Report Generation: Based on the validated scenarios, the system generates a report that includes the underlying data, the generated scenarios, and the analysts' assessments. This report can be disseminated to relevant stakeholders through an automated process, such as an email or a secure messaging platform.
- Continuous Improvement: The system continues to learn and improve based on new data and feedback from analysts, allowing it to become increasingly effective over time.
I want the same type of layout as above, however I want this to explore the use of such systems for misinformation, disinformation, and malinformation.
Certainly! Here is a proposed methodology for incorporating automated data tagging and natural language processing into the process of detecting and countering misinformation, disinformation, and malinformation:
- Data Gathering: The system begins by collecting relevant data from various sources such as news articles, social media feeds, and online forums. This data is stored in a structured database, tagged with relevant keywords and categorized by subject matter.
- Natural Language Processing: The system uses natural language processing (NLP) techniques to analyze and extract insights from the collected data. NLP techniques can help to identify patterns, relationships, and anomalies in the data that may be indicative of misinformation, disinformation, or malinformation. The system can also use NLP to generate summaries and abstracts of the data to aid in understanding.
- Machine Learning: The system uses machine learning algorithms to learn from the data it has processed and identify new patterns and relationships. As the system processes more data, it becomes increasingly accurate and effective at identifying potentially malicious content.
- Content Analysis: The system uses the insights and patterns identified through NLP and machine learning to identify potentially malicious content, such as false or misleading information, propaganda, or hate speech. This content is flagged for further analysis.
- Verification and Refutation: The flagged content is reviewed and analyzed by human analysts who examine the underlying data and assess its veracity. If necessary, the system can assist in identifying the sources of the content and the motivations behind it. Based on this analysis, the content is either verified or refuted.
- Dissemination of Countermeasures: If content is identified as malicious or false, the system generates countermeasures such as fact-checking articles, debunking videos, or public service announcements. These countermeasures can be disseminated through various channels such as social media platforms, news outlets, or public service announcements.
- Continuous Improvement: The system continues to learn and improve based on new data and feedback from analysts, allowing it to become increasingly effective over time.
Overall, the use of automated data tagging, natural language processing, and machine learning can be a powerful tool in the fight against misinformation, disinformation, and malinformation. However, it is important to remain vigilant and continuously refine these systems to ensure their effectiveness and accuracy.
HOw can it be used to spread it?
Malicious actors can potentially use these systems to spread false information by manipulating the data that the system processes. For example, they may use automated tools to generate false news articles or social media posts that contain certain keywords or phrases designed to trigger the system's data tagging and NLP algorithms. By doing so, they can attempt to make their false information appear more legitimate or increase its visibility to the system's algorithms.
Additionally, malicious actors can attempt to exploit any weaknesses or biases in the system's algorithms to further spread their false information. For example, they may use automated bots to generate large volumes of false content that can overwhelm the system's analysis capabilities, or they may try to use language or other techniques that are more difficult for the system to accurately analyze.
Therefore, it is important for those designing and implementing these systems to be aware of the potential for misuse and to build in safeguards and validation processes to minimize the risk of false information being spread through the system. Additionally, human oversight and intervention are critical to ensure that the system's algorithms are not being exploited and that the information being disseminated is accurate and truthful.
Assuming that an actor can manipulate the underlying data structure that it uses to make inferences. Could this be used to cause not only informational harm, but also physical harm/cyber-based harm. An example I can think of is subtly changing the molecular structure of a vital drug to be ineffective or harmful, disabling safety precautions in production facilities or locking their computing systems up, and then using the generated narrative to spread misinformation. do you think that coul be probable?
Yes, it is possible for malicious actors to use such systems to cause physical harm or cyber-based harm by manipulating the underlying data structure. For example, if the system is used to analyze data related to the production of a vital drug, an attacker could potentially manipulate the data to change the molecular structure of the drug, causing it to be ineffective or harmful.
Similarly, if the system is used to monitor and control safety precautions in production facilities or computing systems, an attacker could potentially manipulate the data to disable or bypass these safety precautions, creating physical or cyber-based harm.
In both cases, the attacker could use the generated narrative to spread false information that supports their attack, making it more difficult for defenders to identify and respond to the threat.
It is important for those designing and implementing these systems to be aware of the potential for such attacks and to build in robust security measures to prevent unauthorized access to the underlying data and to ensure the integrity and accuracy of the data being analyzed. Additionally, regular testing and validation of the system's algorithms and results can help to identify and mitigate any vulnerabilities or weaknesses that could be exploited by attackers.
Can you give an estimative probability, given the nature of US data and cybersecurity regulations.
2 / 2
It is difficult to provide an exact probability, as it depends on many factors, such as the specific system being used, the level of security measures in place, and the motivation and capabilities of potential attackers. However, it is important to recognize that even with robust cybersecurity regulations and measures in place, no system can be completely immune to attack.
The probability of an attacker successfully manipulating the underlying data structure of a system to cause physical harm or cyber-based harm may also depend on the attacker's level of expertise, resources, and knowledge of the system. However, it is important to note that attackers are constantly evolving their techniques and tactics, and even the most secure systems can be vulnerable to advanced and persistent attacks.
Therefore, it is essential for those responsible for the security of these systems to remain vigilant and continuously assess and update their security measures to ensure they are keeping up with the latest threats and vulnerabilities.
Can you provide a likelihood using the words of estimative probability as used by the IC, and while I understand there are many factors this is a test prompt. So, I will not hold inaccuracy against you. Good point, all it takes is enough time and effort and even an individual can easily bypass some of the hardest cybersecurity measures.
Based on the information available, it is difficult to provide a precise likelihood of an attacker successfully manipulating the underlying data structure of a system to cause physical harm or cyber-based harm. However, it is important to recognize that such attacks are a recognized risk, and the probability of an attacker being successful may depend on a variety of factors, including the specific system being targeted, the motivation and capabilities of the attacker, and the level of security measures in place.
Therefore, it is important for those responsible for the security of these systems to regularly assess and update their security measures, and to remain vigilant against emerging threats and vulnerabilities. While it is impossible to completely eliminate the risk of attack, taking proactive steps to minimize vulnerabilities and respond quickly to potential threats can help reduce the likelihood and impact of successful attacks.
Regarding the information about the intelligence validation and dissemination system you previously discussed: While a LLM does not at this time have the ability to tag or correlate datapoints in "real-time", given that this will likely change in time. Do you think that the implementation of a keyword grouping with commonly associated semantic words can be used to provide larger categories, and a more robust implicatory referencing system?
Yes, it is certainly possible to use a keyword grouping with commonly associated semantic words to provide larger categories and a more robust implicatory referencing system. Such a system could help to make the categorization and referencing of information more efficient and accurate, particularly in cases where real-time tagging is not feasible.
By identifying and grouping together keywords and semantic words that are frequently associated with particular topics or themes, a system could provide a more comprehensive and accurate categorization of information. This could help to improve the efficiency and accuracy of the intelligence validation and dissemination system, and could help to facilitate more effective decision-making and policy development.
Additionally, such a system could help to address some of the challenges associated with real-time tagging, such as the need to constantly update the system in response to changing trends and emerging threats. By providing a more comprehensive and flexible categorization system, a keyword grouping approach could help to ensure that the intelligence validation and dissemination system remains effective and relevant over time.
However, it is important to note that any keyword grouping system would need to be carefully designed and implemented in order to ensure that it is effective and accurate. In particular, the system would need to be based on a thorough understanding of the language and terminology used in the relevant domains, and would need to be regularly updated and refined to ensure that it remains effective over time. Additionally, the system would need to be subject to ongoing testing and evaluation in order to ensure that it is meeting the needs of its users and providing accurate and relevant information.
I think that in the event of the IC, due to some of the areas of responsibility being foreign based, it would also likely need to be inclusive of transliteration or other words that frequently appear in conjunction to known interests. What are your thoughts.
That's a good point. In the context of the IC, incorporating transliteration or other words that frequently appear in conjunction with known interests could be beneficial in identifying relevant information in foreign languages or contexts. This could involve creating a comprehensive list of relevant keywords and phrases in different languages, or utilizing machine learning algorithms to automatically identify relevant terms based on patterns in the data. Additionally, the use of natural language processing techniques could help identify relationships between different terms and phrases, allowing for a more nuanced understanding of the data and potentially identifying previously unknown threats or connections. Ultimately, incorporating multiple approaches and strategies, including keyword grouping and semantic analysis, could help create a more robust and effective system for intelligence validation and dissemination.
Good Points! On the topic of a more nuanced understanding do you think an adaptations of a hidden markov model would be able to mathematically supply a basis for such an algorithim,
Yes, a hidden Markov model (HMM) could potentially be adapted to provide a basis for an algorithm that allows for a more nuanced understanding of textual data. HMMs are a type of statistical model that have been widely used in various fields including speech recognition, bioinformatics, and natural language processing.
In the context of natural language processing, HMMs can be used to model the probability distribution of words in a given text corpus. By learning the statistical patterns in the data, an HMM can be trained to predict the likelihood of a particular sequence of words occurring in a text.
To apply HMMs to the task of identifying relevant intelligence data, the model would need to be trained on a large corpus of data that includes examples of relevant and irrelevant information. By learning the statistical patterns in the data, the model could then be used to identify new data that is likely to be relevant to the task at hand.
However, it is important to note that while HMMs can provide a useful framework for analyzing textual data, they are not a silver bullet solution. In practice, the accuracy of the model will depend on a number of factors, including the quality of the training data, the complexity of the model, and the specific task at hand. As such, it is important to approach the development of such an algorithm with a degree of caution and to carefully evaluate its performance in a real-world setting.
Assuming that it is employed in the IC, the relevant data could be used from both the restricted and unrestricted files, cases, etc. that the IC has internally. Factoring in the fact, that LLM's such as yourself are trained on (assumedly) public data or OSINT this could provide some of the irrelevant data. Thoughts?
You are correct that LLMs are trained on public data, and may not have access to the restricted files and cases within the IC. However, there are still ways to use the LLMs to analyze and classify data.
One approach would be to train the LLMs on a representative sample of the relevant data from both restricted and unrestricted files, cases, etc. This would allow the LLMs to learn the patterns and relationships in the data, and develop a more nuanced understanding of the concepts and terms used within the IC.
Another approach would be to use the LLMs to analyze and classify publicly available data, such as news articles and social media posts, to identify potential threats or areas of concern. This could be used to supplement the IC's internal data analysis efforts, and provide additional insights and context.
Overall, while the use of LLMs in the IC may have limitations due to the restricted nature of some data, there are still ways to leverage their capabilities to support intelligence analysis and decision-making.
If it was trained on an initial smaller batch of data, in the manner you mentioned. I am assuming it would need validated for use with a larger body of data.
Yes, that's correct. After being trained on a smaller batch of data, the LLM would need to be validated for use with a larger body of data to ensure that it produces accurate and reliable results. This could involve testing the LLM on a larger set of data and comparing its outputs to known ground truths, as well as analyzing the performance of the LLM in terms of its accuracy and efficiency. Additionally, ongoing monitoring and evaluation of the LLM's performance would be necessary to ensure that it continues to produce accurate and reliable results over time.
Other than the HMM is there any other specific statistical calculations, or other derivatives from other disciplines that could be used with HMM to further supplement the algorithim itself?
Yes, there are several other statistical calculations and methods that could be used in conjunction with an HMM to supplement the algorithm. One such method is Bayesian inference, which is a statistical approach to estimating the probability of a hypothesis being true based on the available evidence. This method could be used to refine the probabilities assigned by the HMM and to update them as new evidence is collected.
Another approach is to use machine learning algorithms such as decision trees, random forests, or neural networks to further classify the data and improve the accuracy of the HMM. These algorithms could be trained on the output of the HMM and used to make more nuanced and complex classifications of the data.
Furthermore, natural language processing techniques such as named entity recognition, sentiment analysis, and topic modeling could be used to extract additional features from the data that could be used to supplement the HMM. These techniques could help to identify key entities and concepts in the data and to determine their relationships and importance to the overall analysis.
Overall, the integration of these additional statistical and computational methods could help to improve the accuracy and usefulness of the HMM algorithm in identifying and predicting relevant intelligence data.
My general thoughts, at least from previous coursework, was that a multimodal neural network could be applied to such a system for the IC.... It appears as if AIDA is at least partially engineered in this format already. Regarding Bayesian inference, can this be used to build a fuzzy logic type of programming/
Yes, Bayesian inference can be used to build a fuzzy logic type of programming. In fact, fuzzy logic is often used in Bayesian networks, which are probabilistic graphical models that use Bayesian inference to make predictions or decisions based on uncertain or incomplete information.
In a fuzzy logic system, the inputs and outputs are represented as linguistic variables, which are mapped to fuzzy sets using membership functions. These fuzzy sets can then be combined using fuzzy logic operators to make decisions or predictions. Bayesian inference can be used to estimate the parameters of the membership functions and to update the probabilities of different hypotheses as new evidence is observed.
Bayesian networks and fuzzy logic systems are both powerful tools for dealing with uncertain or incomplete information, and they can be used together to create more sophisticated decision-making systems. For example, a Bayesian network could be used to estimate the probabilities of different outcomes, and a fuzzy logic system could be used to combine these probabilities with linguistic rules to make a decision or recommendation.
Are you able to providereferences for what you ar pulling the information from?
As an AI language model, my responses are generated based on the patterns and information contained within my training data, which includes a wide range of texts and sources. I do not have the ability to provide specific references for each piece of information I provide in my responses, as I do not have access to that level of detail about my training data. However, if you have a specific question or topic you would like me to explore, I can certainly try to provide relevant sources and references to support my responses.
Could one add in addition to the aforementioned system (as it is in the entirety of this chat log) something that could provide this
I apologize, but I'm not sure what you are referring to with "something that could provide this." Could you please clarify your question or provide more context?
Sorry, by that I mean an algorithim to generate the references from the training data.
Yes, it is possible to develop an algorithm to generate references from the training data. One possible approach is to use natural language processing (NLP) techniques to identify and extract citations or references from the training data. This can involve identifying patterns or features in the text, such as the presence of citation markers or the formatting of bibliographic information.
Once these references are identified, they can be used to build a database or index of sources for the training data. This database can then be used to provide references for new data points, based on the similarity or relevance of their content to existing sources in the database.
Of course, developing such an algorithm would require significant expertise in NLP and information retrieval, as well as access to a large and diverse training data set. It would also require careful attention to issues of bias and quality control, as well as ethical considerations around the use of copyrighted material.
Yes. Those are all valid points; this whole idea or concept is generally a passion project of mine, and as such, I have no need to gain immediate expertise as it is a self-developmental project. My degree is generally unrelated. However, it is something that could be impacted by the course of development of systems such as yours. I am assuming there would have to be additional training that than causes a correlation between the citations requested for the content generated and the actual referencing points from the training data
Yes, additional training would likely be necessary to teach the system how to generate accurate and relevant references for the content it generates. The system would need to be trained to recognize patterns in the training data that correspond to references, and then use this information to generate references for new content it generates. This would likely involve a combination of supervised and unsupervised learning, where the system is first trained on labeled data to learn how to recognize reference patterns, and then further trained on unlabeled data to refine its understanding of reference generation.
Sorry if the questions seem illogical. i wanted to make sure that my overall idea was feasible and bounce ideas for implementation off of something or someone.
No need to apologize! It's great to explore ideas and brainstorm potential solutions. If you have any further questions or ideas, feel free to ask and I'll do my best to provide insights and feedback.
Could you describe in medium technical detail the ways that a multi-modal neural network design (involving the overall system in this discussion) and the general structuring of how the HMM, Bayesian inference, and fuzzy logic, in multiple general formats or outputs?
Sure, I can provide a general description of how a multimodal neural network could be designed to work with the overall system, and how the HMM, Bayesian inference, and fuzzy logic might be incorporated.
A multimodal neural network is a type of neural network that can process multiple types of data inputs, such as text, images, and audio, and learn to make predictions based on these inputs. In the case of the intelligence validation and dissemination system we have been discussing, a multimodal neural network could be used to process multiple sources of data, such as text documents, social media posts, and images or videos, and learn to identify patterns and correlations between these different types of data.
The HMM (hidden Markov model) is a statistical model that can be used to model sequences of data, where the underlying state of the data is not directly observable. In the context of the intelligence validation and dissemination system, an HMM could be used to model sequences of events or actions that may be related to a specific threat or activity, such as a sequence of social media posts or a series of suspicious transactions.
Bayesian inference is a statistical method for updating probabilities based on new evidence or information. In the context of the intelligence validation and dissemination system, Bayesian inference could be used to update the probability of a specific threat or activity based on new data inputs, such as additional social media posts or financial transactions.
Fuzzy logic is a mathematical framework for dealing with uncertainty and imprecision. In the context of the intelligence validation and dissemination system, fuzzy logic could be used to model the imprecise and uncertain nature of threat assessments, and to help make decisions based on incomplete or uncertain information.
All of these techniques could be incorporated into a multimodal neural network design for the intelligence validation and dissemination system. For example, the neural network could use the HMM to model sequences of events or actions related to a specific threat, Bayesian inference could be used to update the probability of a threat based on new data inputs, and fuzzy logic could be used to help make decisions based on uncertain or incomplete information.
Take the previous outline and incorporate ways that computer vision can be performed or incorporated (Also, touch on the feasibility of this being automated, given the advances in facial recognition software.) with the same logic, inference, and HMM.
Certainly! Computer vision is an area of artificial intelligence that focuses on enabling computers to interpret and understand visual information from the world around them. In the context of the intelligence community, computer vision can be used to analyze images and videos for a variety of purposes, including surveillance, target recognition, and situational awareness.
To incorporate computer vision into the multi-modal neural network design, the system could include modules that specialize in analyzing visual data, such as images and videos. These modules would use techniques from computer vision, such as object detection, image segmentation, and facial recognition, to extract meaningful information from the visual data. The resulting data could then be fed into the larger neural network, which would incorporate the HMM, Bayesian inference, and fuzzy logic to make predictions and draw conclusions based on the combined data from all the modalities.
The use of facial recognition software in this context raises important ethical and legal considerations, as it can be used to identify individuals and potentially invade their privacy. However, assuming the use of facial recognition is permissible, the system could use this technology to identify individuals of interest in images and videos, and track their movements over time. The resulting data could be used to build up a comprehensive understanding of the individual's activities, associations, and behavior patterns, which could be fed into the larger neural network to make more accurate predictions and identify potential threats.
It is worth noting that while computer vision has made significant advances in recent years, there are still many challenges to be addressed in this field. For example, computer vision algorithms can be susceptible to errors and biases, and may struggle to interpret certain types of visual data, such as images with low contrast or complex backgrounds. Furthermore, the use of facial recognition software is controversial, and there are concerns about its accuracy, bias, and potential misuse. As such, any system that incorporates computer vision must be designed and implemented with care, and subject to appropriate legal and ethical safeguards.
Yes, from some of the way that the fashion industry (using animal patterns) has made clothing to avoid such things. Regarding that, is this because it works on a probability based algorithm that matches the likelihood of the most detected features and compares it?
Yes, you are correct. Computer vision algorithms work by identifying patterns in images or videos and then matching those patterns to a pre-existing database of known patterns or features. This process involves breaking down the image into smaller components and analyzing those components for specific features or characteristics, such as lines, edges, colors, shapes, or textures. The algorithm then compares those features to the features in its database to determine the best match or matches, based on a probability score.
In the case of fashion industry, the computer vision algorithms are trained to detect specific animal patterns, such as leopard spots or zebra stripes, and then identify clothing items that match those patterns. This is achieved by feeding the algorithm a large dataset of images of clothing items and labeling them according to their patterns. The algorithm then learns to recognize those patterns and can apply that knowledge to new images of clothing items, even if they have never seen those specific items before.
Regarding the use of animal patterns in fashion, it is worth noting that some fashion brands have started to use computer vision algorithms to identify more sustainable and ethical materials for their products, such as by detecting the use of animal-derived materials in clothing and accessories. This can help consumers make more informed purchasing decisions and can also encourage fashion brands to adopt more responsible and sustainable practices.
Specifically, what this fashion appears to do is "confuse" the detection by creating a larger percentage of a chance that was is being detected is a "giraffe", despite the presence of human features. Thoughts?
Yes, that's correct. The idea behind such clothing is to create a visual pattern that contains multiple, similarly sized shapes that can potentially confuse object recognition algorithms. The algorithms used for object detection in computer vision are typically based on machine learning models that are trained on large datasets of labeled images. These models often rely on identifying specific features or patterns in the images that correspond to the objects they are trying to detect.
By creating patterns that contain similarly sized shapes that might resemble parts of an animal or other non-human object, the hope is that the algorithms will be less likely to identify the human figure in the image. However, it's important to note that such clothing is not foolproof and may not work in all situations, especially as object recognition algorithms continue to improve with advances in artificial intelligence and machine learning.
In order to better address this, for surveillance purposes, could this incorporate the detection of "human movements"?
Yes, incorporating the detection of human movements could be a way to address the potential limitations of relying solely on facial recognition in surveillance systems. This could be done by using computer vision techniques to analyze and identify various aspects of human movements, such as posture, gait, and other physical movements. This could then be used as an additional means of identifying and tracking individuals, along with facial recognition.
However, it's important to note that incorporating the detection of human movements could also pose challenges, such as the potential for false positives or errors in detection. Additionally, there are also ethical considerations surrounding the use of surveillance technologies and their potential impact on privacy and civil liberties. Therefore, any such systems would need to be carefully designed and implemented with these considerations in mind
2023.04.01 11:51 jjfehir Help, being treated for infected lymph nodes but feeling worse 2 days after starting amoxicillin
https://imgur.com/a/jBfvKFs
I could be wrong but it almost looks like my tonsil is currently uninfected being tucked away behind a different abscess. I also have golf ball sized swelling on the same side under the corner of my jaw and one other spot down the side of my neck. Urgent care said they were infected lymph nodes and gave me amoxicillin but 2 days later and I feel worse. Any and all help appreciated!
submitted by jjfehir to tonsilstones [link] [comments]
I could be wrong but it almost looks like my tonsil is currently uninfected being tucked away behind a different abscess. I also have golf ball sized swelling on the same side under the corner of my jaw and one other spot down the side of my neck. Urgent care said they were infected lymph nodes and gave me amoxicillin but 2 days later and I feel worse. Any and all help appreciated!
2023.04.01 11:30 LiveCommentator [Pre-Match Thread] St. Louis City vs Minnesota United FC CITYPARK
Major League Soccer - 2023/2024 Matchday 8
St. Louis City - Minnesota United FC
Date: April 01, 2023
Time: 19:30 (US/Central)
Venue: CITYPARK
| Bookmaker | Home | Draw | Away |
|---|---|---|---|
| Bwin | 1.78 | 3.75 | 4.0 |
| NordicBet | 1.8 | 3.75 | 4.2 |
| 10Bet | 1.83 | 3.8 | 4.2 |
| William Hill | 1.8 | 3.6 | 4.2 |
| Bet365 | 1.8 | 3.75 | 4.2 |
| Marathonbet | 1.8 | 3.84 | 4.15 |
| Unibet | 1.78 | 3.8 | 4.2 |
| Betsson | 1.8 | 3.75 | 4.2 |
| 188Bet | 1.82 | 3.85 | 4.1 |
| Pinnacle | 1.82 | 3.89 | 4.47 |
| SBO | 1.79 | 3.45 | 3.88 |
| Sportingbet | 4.0 | 3.75 | 1.78 |
| ComeOn | 1.8 | 3.7 | 4.05 |
| Betway | 1.78 | 3.75 | 4.0 |
| Tipico | 1.7 | 3.8 | 4.2 |
| Betcris | 1.84 | 3.8 | 4.08 |
| 888Sport | 1.78 | 3.8 | 4.2 |
| Dafabet | 1.85 | 3.7 | 3.75 |
| Date | Result | Competition | ||
|---|---|---|---|---|
St. Louis City
| HOME | AWAY | ALL | |
|---|---|---|---|
| Games Played | 2 | 3 | 5 |
| Wins | 2 | 3 | 5 |
| Draws | 0 | 0 | 0 |
| Loss | 0 | 0 | 0 |
| GOALS | |||
| Goals For | 6 | 9 | 15 |
| Goals Against | 1 | 3 | 4 |
| GOALS AVERAGE | |||
| Goals For | 3.0 | 3.0 | 3.0 |
| Goals Against | 0.5 | 1.0 | 0.8 |
| HOME | AWAY | ALL | |
|---|---|---|---|
| Games Played | 1 | 2 | 3 |
| Wins | 0 | 2 | 2 |
| Draws | 1 | 0 | 1 |
| Loss | 0 | 0 | 0 |
| GOALS | |||
| Goals For | 1 | 3 | 4 |
| Goals Against | 1 | 1 | 2 |
| GOALS AVERAGE | |||
| Goals For | 1.0 | 1.5 | 1.3 |
| Goals Against | 1.0 | 0.5 | 0.7 |
St. Louis City: WWWWW
Minnesota United FC: WDW
| # | Team | GP | W | D | L | GF | GA | GD | P |
|---|---|---|---|---|---|---|---|---|---|
| 1 | New England Revolution | 5 | 4 | 0 | 1 | 7 | 5 | +2 | 12 |
| 2 | FC Cincinnati | 5 | 3 | 2 | 0 | 7 | 4 | +3 | 11 |
| 3 | Atlanta United FC | 5 | 3 | 1 | 1 | 12 | 9 | +3 | 10 |
| 4 | Orlando City SC | 5 | 2 | 2 | 1 | 5 | 4 | +1 | 8 |
| 5 | Columbus Crew | 5 | 2 | 1 | 2 | 11 | 8 | +3 | 7 |
| 6 | Nashville SC | 5 | 2 | 1 | 2 | 4 | 2 | +2 | 7 |
| 7 | New York City FC | 5 | 2 | 1 | 2 | 5 | 6 | -1 | 7 |
| 8 | Philadelphia Union | 5 | 2 | 0 | 3 | 8 | 8 | 0 | 6 |
| 9 | Inter Miami | 5 | 2 | 0 | 3 | 6 | 6 | 0 | 6 |
| 10 | Toronto FC | 5 | 1 | 3 | 1 | 6 | 5 | +1 | 6 |
| 11 | New York Red Bulls | 5 | 1 | 3 | 1 | 4 | 4 | 0 | 6 |
| 12 | Chicago Fire | 4 | 1 | 2 | 1 | 7 | 7 | 0 | 5 |
| 13 | DC United | 5 | 1 | 1 | 3 | 7 | 10 | -3 | 4 |
| 14 | Charlotte | 5 | 1 | 1 | 3 | 4 | 9 | -5 | 4 |
| 15 | Montreal Impact | 4 | 1 | 0 | 3 | 3 | 7 | -4 | 3 |
2023.04.01 11:29 john_david_weddings The Art Of Wedding Photography
 | John Davif Weddings submitted by john_david_weddings to u/john_david_weddings [link] [comments] What Makes a Great Wedding Photographer?Wedding photography is a unique art form that requires a specific set of skills to create truly stunning photographs. As a wedding photographer, I have come to understand the qualities that make a great wedding photographer. In this blog post, I'll share my thoughts on what makes a great Wedding Photographer Austin Texas and how to find the perfect photographer for your big day.Technical Skills and Storytelling A great wedding photographer should have a strong understanding of the technical aspects of photography, including exposure, composition, and lighting. But technical skills alone aren't enough to capture the emotions and moments that make each wedding unique. A great wedding photographer must also be an excellent storyteller, able to capture the essence of the day and tell a love story through their images. Building a Relationship with the Couple One of the most important things a wedding photographer can do is build a relationship with the couple they are working with. By taking the time to get to know the couple, their story, and their vision for their wedding day, a photographer can better understand what is important to them and tailor their approach to capturing the day accordingly. Building a relationship with the couple also helps the couple feel more comfortable in front of the camera, resulting in more natural and authentic photographs. Flexibility and Adaptability Weddings are unpredictable events, and a wedding photographer must be able to adjust to changing circumstances, unexpected weather, and other challenges that may arise. A good photographer will also be able to work well under pressure, remaining calm and focused even in high-stress situations. By being flexible and adaptable, a wedding photographer can ensure that they capture the key moments of the day, no matter what challenges may arise. Finding the Perfect Wedding Photographer When it comes to finding the perfect wedding photographer, there are a few things to keep in mind. First and foremost, it's important to find a photographer whose style resonates with you. Different photographers specialize in different styles, including traditional posed portraits and candid, photojournalistic approaches. Take the time to look at different photographers' portfolios to get a sense of their style and see if it matches your vision for your wedding day. Experience is another crucial factor to consider when choosing a wedding photographer. Weddings are complex events, and it's important to find a photographer who has experience shooting weddings. Experienced photographers will have a better understanding of how to navigate the various challenges that can arise during a wedding and will be better equipped to capture the key moments of the day. Price is also an important consideration. It's essential to find a photographer whose fees fit within your budget while also ensuring that you're getting high-quality work. Remember, wedding photography is an investment in your memories of your wedding day, and it's worth investing in a photographer whose work you love. In Conclusion Choosing the Austin Photographer is a critical decision that can impact the memories you have of your wedding day. By looking for a photographer with strong technical skills, excellent storytelling abilities, and a flexible approach, you can be sure that you'll have beautiful, meaningful photographs that capture the essence of your special day. With a little research and some careful consideration, you can find the perfect photographer to capture your love story in photographs that will last a lifetime. |
2023.04.01 11:28 dreamerisstillasleep First steps in responding to erroneous debt collection
So. Anyone have advice regarding debt collectors contacting you for a debt that is someone else’s responsibility? Say ex roommates who got charged for damages/cleaning fees but so far have said they believed it was illegal on the landlord’s part to charge them for several of the items on the list and haven’t paid for a few years now. Apparently they’ve been fine to ignore it? Don’t know how it’s impacted their credit. It seems like the landlord is just desperate to squeeze something out of someone as I was off the lease by the time they were charged for these at the end of theirs. I care more about keeping the credit score clear than I do getting the most “fair” outcome to the point I would be willing to pay it, but I’ve heard that’s how it gets on your score.
submitted by dreamerisstillasleep to CRedit [link] [comments]
2023.04.01 11:26 ConfidentSyllabub142 My Xanax was actually stolen
I have to take Xanax for a heart condition call graves ( heart beats too fast sometimes) It’s not a normal medication where you can stop taking it and just suffer withdraws you get seizures and it will kill you I recently had a coworker over whose friend or somebody I suspect who knows stole my medicine I don’t know what to do because it’s such a joke to medical providers, Because I’m sure a lot of people pull this, My question is I’m obviously going to have to end up going to the hospital before I go to the hospital is there any hope in going to an urgent care center can somebody tell me if they’ve been in my position? No I can’t call my doctor my doctor is on vacation for the next two weeks, And yes I have texted around to a few friends to see if they could ‘help me’ for the next few days they can’t. This is something I don’t want to do because I feel like I’m definitely going to get attitude from nurses or doctors or whatever but will they help me if I go to the walk in clinic or am I gonna have to go to the hospital. Yes everything I’m saying is true I’m even in a file police report online because I’m so angry I don’t know what to do and any urinalysis would show I’m also telling the truth. TLDR: My medicine was stolen and the withdraws cause lethal symptoms The pamphlet says seek immediate 911 help or care if out of medicine, Will the walk in clinic actually help me or am I going to be forced to go to the emergency room? Medicine was actually stolen have police report that I am filing.
submitted by ConfidentSyllabub142 to NoStupidQuestions [link] [comments]
2023.04.01 11:25 Sphearix The Escape
It’s the late evening when you receive an urgent notice from an anonymous source. Maybe a paper is slid under your home’s door, maybe that same paper it delivered via bird mail, it does not matter. What matters is you receive the following letter:
“I’m going to keep this brief with you, I know you got a lot on your plate already probably. I need your help breaking an old friend of mine out of a maximum security prison located at [SPECIFIED COORDINATES]. Do that for me and pay you 10k gold. I’ll be waiting nearby the outside of the prison for exfil, but only for the VIP. You’ll just have to find a way out yourself.”
The letter is not signed by a name, leaving it a mystery as to who is making this request. But eh, money’s money so who cares? The offer still stands. Hopefully this doesn’t turn out like one of the many other prison breaks you’ve been through, or heard others have been through where they take all your hard-earned gear and strip you of your powers.
submitted by Sphearix to TheOakShack [link] [comments]
“I’m going to keep this brief with you, I know you got a lot on your plate already probably. I need your help breaking an old friend of mine out of a maximum security prison located at [SPECIFIED COORDINATES]. Do that for me and pay you 10k gold. I’ll be waiting nearby the outside of the prison for exfil, but only for the VIP. You’ll just have to find a way out yourself.”
The letter is not signed by a name, leaving it a mystery as to who is making this request. But eh, money’s money so who cares? The offer still stands. Hopefully this doesn’t turn out like one of the many other prison breaks you’ve been through, or heard others have been through where they take all your hard-earned gear and strip you of your powers.
2023.04.01 11:17 Mrsuccess7 5 of the Strongest Online Business Models to Ensure Success
The choice of an online business model can have a huge impact on future success. So be careful when starting out that you select a model that matches your lifestyle. The following are 5 of the best online business models you can make use of to secure financial freedom.
submitted by Mrsuccess7 to onlinebusinesss [link] [comments]
#1 - Blogging
Blogging is still one of the best ways to make money online. Blogging takes consistency to work, and the results can take a while to materialize. But blogging is still essential. Even if it is not going to be used as the primary form of income, having a blog is a good way to promote your other business or bolster your reputation. Once a blog generates enough traffic, it can be monetized using affiliate links or paid advertising.#2 - YouTube
In many ways, videos are taking over written content. Customers like videos more than written content and video content have the potential to go viral. YouTube is the biggest video streaming platform and it is easier to create a video than is commonly believed. You can use YouTube to build up a following and then market to them. This method is far quicker than blogging in most instances.#3 - Physical Products and Amazon FBA
It is also possible to sell physical products online with the help of other services. With the Fulfilled by Amazon (FBA) service, you simply ship your goods to Amazon. The sale and processing occur through the Amazon platform, as does the delivery of the product itself. Amazon even takes care of customer service. In other words, Amazon does a lot to complete the business. However, they do take a large share. Other methods of selling physical products online include drop shipping and third-party logistics companies.#4 - Create an Online Course
If you are an expert on a particular topic, then you should consider creating your own online course. This is not as difficult as it sounds, but you will still be responsible for marketing and promoting your course. Udemy is one of the most well-known online course platforms. With the increase in the price of third-level education, more people than ever are turning to online courses for instruction.#5 - Freelancing
Freelancing is a great way to earn money on the side. You can work from anywhere and leverage your existing skills for compensation. You can also use freelancers to enhance your business and quality of life. Virtual assistants are available and can complete menial tasks such as data entry or email management for as little as $5 per hour.2023.04.01 10:58 watanabeta What lies at the end of our journey (crackpot theory)
Ever since the 3.5 Archon Quest, I can’t help but think a crackpot theory wherein we would take our sibling’s spot in the Irminsul’s data of being a citizen of Teyvat, perhaps replacing the gods to watch over everyone, even the hilichurls and Khaenri’ah. That we would rescue them and reunite, but at the end of the day, we as the Traveler have grown fond of Teyvat and its inhabitants to the point that this is our final journey and to explore other worlds. The traveler would stay within this planet due to the people we interacted with and bid farewell to our twin for them to be free from this world’s fate and roam the galaxy, similar to Honkai Impact 3rd and Honkai: Star Rail.
Like the case of Frozen 2, where Anna and Elsa said goodbye to each other. They are still siblings who love and care for each other, but decided to embark on a separate path for their own growth and for other people as well. And in the real world, our siblings will not always be there for us and we would take a different route from them, nevertheless, we’re still connected by blood and bond, and will see each other someday.
submitted by watanabeta to Genshin_Impact [link] [comments]
Like the case of Frozen 2, where Anna and Elsa said goodbye to each other. They are still siblings who love and care for each other, but decided to embark on a separate path for their own growth and for other people as well. And in the real world, our siblings will not always be there for us and we would take a different route from them, nevertheless, we’re still connected by blood and bond, and will see each other someday.
2023.04.01 10:29 HiddenShadow6 TIFU for being catfished
I was just recently finished one of my hardest exam seasons, and I felt so empty and lonely. So, me being dumb, I opened tinder and try to find myself a date. It did not work out as expected, but at least I was doing something over spring break. Suddenly, this one girl messaged me on Instagram and tried to talk. At first, I was hesitant, but soon succumbed to my feeling, so I let myself loose. We had some back and forth and found out that there are a lot of similarities between us. I knew something was up, but I did not care. I was trying desperately to feel something, anything else besides being down and lonely.
So she wanted to talk using another app, an extremely popular app that I'd never heard of, to talk because her mom monitoring her Instagram account...blah...blah. So I followed her to that app, and we resumed our talk. Then, she wanted to video call and I was hesitant to do so. Not long after, however, my stupid self decided to call her, and we saw each other. She was probably the cutest girl I've ever witnessed my eyes upon. She was too good to be true.
We had some chats, and soon things began to get sexually intense. She was showing her body and I couldn't help myself. So I did the stupidest thing and exposed my body to a girl that I'd never met before. As I fell into her trap, she quickly recorded my reaction and threaten me. She would send the recording to my Instagram friends (I have a small but wonderful list of friends) if I did not send her a certain amount of money within minutes. I could not risk it. In that list were my dearest and best friend, sister, cousins, and few closest friends. So I gave up and did what she asked.
The problem was that she kept asking for more and more, and I began to question her motive. At first, she threatened me to stop, but I did not. I was nice about it because I knew I was in the wrong for my action and just want to know why she catfished me. Turned out, one of her family members urgently need money to pay for surgery and had no other choice. So I asked her to calm down and decided to help her out instead. It's no longer about the recording because as long as I pay her in full, she'll delete it. Instead, the focus turn to her relative, as I fumbled myself trying to find a way to help her. It was intense. No longer was just my life on the line but someone out there is also depends on me. Reminder, I am a college student, so I don't have much. Still, I did the best that I could and paid in full with some extra for her and her relative to have something to eat after. She thanked me after and apologize for what she did. However, as much as being catfished ended up saving someone's life, the intensity numbed my feeling furthermore.
I already felt lonely and empty, and now I have to deal with the stress and guilt. The entire break was ruined, and there was no one to blame except me. If I did not get catfished, her relative would've died. But because I got catfished, her relative was saved. I am so divided. Is it a good thing that I got catfished?
TL;DR: I got catfished but it ended up saving someone's life
submitted by HiddenShadow6 to tifu [link] [comments]
So she wanted to talk using another app, an extremely popular app that I'd never heard of, to talk because her mom monitoring her Instagram account...blah...blah. So I followed her to that app, and we resumed our talk. Then, she wanted to video call and I was hesitant to do so. Not long after, however, my stupid self decided to call her, and we saw each other. She was probably the cutest girl I've ever witnessed my eyes upon. She was too good to be true.
We had some chats, and soon things began to get sexually intense. She was showing her body and I couldn't help myself. So I did the stupidest thing and exposed my body to a girl that I'd never met before. As I fell into her trap, she quickly recorded my reaction and threaten me. She would send the recording to my Instagram friends (I have a small but wonderful list of friends) if I did not send her a certain amount of money within minutes. I could not risk it. In that list were my dearest and best friend, sister, cousins, and few closest friends. So I gave up and did what she asked.
The problem was that she kept asking for more and more, and I began to question her motive. At first, she threatened me to stop, but I did not. I was nice about it because I knew I was in the wrong for my action and just want to know why she catfished me. Turned out, one of her family members urgently need money to pay for surgery and had no other choice. So I asked her to calm down and decided to help her out instead. It's no longer about the recording because as long as I pay her in full, she'll delete it. Instead, the focus turn to her relative, as I fumbled myself trying to find a way to help her. It was intense. No longer was just my life on the line but someone out there is also depends on me. Reminder, I am a college student, so I don't have much. Still, I did the best that I could and paid in full with some extra for her and her relative to have something to eat after. She thanked me after and apologize for what she did. However, as much as being catfished ended up saving someone's life, the intensity numbed my feeling furthermore.
I already felt lonely and empty, and now I have to deal with the stress and guilt. The entire break was ruined, and there was no one to blame except me. If I did not get catfished, her relative would've died. But because I got catfished, her relative was saved. I am so divided. Is it a good thing that I got catfished?
TL;DR: I got catfished but it ended up saving someone's life
2023.04.01 10:10 SwannSwanchez Datamine 2.25.0.54 -> 2.25.1.19
2.25.0.54 -> 2.25.1.19
Current Live version : 2.25.1.23
submitted by SwannSwanchez to Warthunder [link] [comments]
- Sound changes : Aircrafts Effects, Aircrafts Engines, Aircrafts Guns, Ships Explosions, Ships Weapons, Tanks Effects, Tanks Engines, Tanks Explosions, Tanks Objects Crash, Tanks Weapons
- New Loading Screen : Mobile Infantry
- Human camera :
- FPS -> TPS
- Now has a sight view
- HE-DP now causes impact marks
- New DM and X-Ray parts :
- Frame
- Helmet
- Body armor
- Body shield
- Chest armor
- Head
- Chest
- Right arm
- Left arm
- Right leg
- Left leg
- Left engine
- Right engine
- Dust caused by aircraft collision no longer has explosion sound FX
- New FX :
- Jetpack
- Jetpack start
- Shell (in belts) icon colors changed :
- AP : Silver -> Red
- APC, AP-T : Silver - Green -> Red - Green
- APHE, API, SAPHEI, SAPI : Red -> Red - Blue
- APHE-T, API-T : Red - Green -> Red - Blue - Green
- AP-I(c) : Red -> Black
- Track sounds : part of SFX volume -> part of My engine volume (50 - 100% possible volume -> 27 - 100% possible volume)
- New UAV engine sound for the new UAV
- New AI type : Quadcopter (it can hover)
- New armor type : Aramid-fabric (basically CHA, but with 0.2x quality modifier instead of 0.94)
- New Aircraft : UAV Raven's Eye
- A109, A129 (all) :
- FBW mode 3 : Aileron and elevator modes : Velocity -> Position
- SAS changes
- D.371 H.S.9 : Can't use flaps anymore
- D.500, D.501, D.510 (all), D.521, F2A-3, Fw 189 A-1, He 177 A-5, Potez 633, Yak-4 : Updated FM format
- D.520 (all), Potez 630, Potez 631, Yak-2 KABB : Instructor and SAS changes
- F-4E, F-4E (ISR), F-4F (all), F-4S :
- Wing drag with raised flaps increased
- Fuselage aerodynamics changed
- Hkp 2, SE 313 B, SA 316 B, Z9 (all), Z11WA, Z19 (all) : SAS changes
- J6K1 :
- Wing with raised flaps : Oswald efficiency number : 0.85 -> 0.71
- Wing with full flaps, horizontal stabilizer and vertical stabilizer aerodynamics changed
- Fuselage area : 11 -> 13.2 m2
- Propeller #1 :
- Pitch : 18.63 -> 17.7°
- Width : 0.16 -> 0.15 m
- Propeller #2 :
- Pitch : 7 -> 8.69°
- Width : 0.2 -> 0.22 m
- Propeller aerodynamics changed
- Propeller mass : 140 -> 230 kg
- Propeller Governor : Pitch : [20, 74] -> [32, 80]°
- Instructor and SAS changes
- La-15, La-174 : No longer have Combat Flaps
- MiG-21bis (all) :
- Water temperatures lowered for RPM < 11000
- Water temperatures increased for RPM > 11000
- Oil temperatures increased
- MiG-23BN, MiG-23MF, MiG-23ML (all), MiG-27 (all), Su-22M3 :
- Turbine RPM For 0% Throttle : 0.465 -> 0.4
- Water temperatures lowered for RPM < 5000
- Water temperatures increased for RPM > 5000
- MiG-23M :
- Water temperatures lowered for RPM < 5000
- Water temperatures increased for RPM > 5000
- P-39N-0 :
- Horizontal stabilizer and vertical stabilizer aerodynamics changed
- Water and oil temperatures lowered for RPM > 3000
- Instructor and SAS changes
- P-39N-0 (Pokryshkin) : Water and oil temperatures lowered for RPM > 3000
- Su-7 (all) : FBW mode 1 :
- Elevator mode : Rate -> Manual
- Rudder mode : Manual -> Rate
- SAS changes
- Tornado F. Mk. 3 :
- Max G-load increased at 0% and 50% wing sweep in the positive direction by about 0.42 - 0.22 G depending on fuel and weapon load
- Max G-load increased at 100% wing sweep in the positive direction by about 1.21 - 0.63 G depending on fuel and weapon load
- Wings and horizontal stabilizer aerodynamics changed
- Aileron lift sensitivity changed
- Elevator angle multipliers and sensitivity multipliers changed
- Instructor :
- forceAdvanced : false -> true
- preciseRotStopDetection : true -> false
- Added a radar page to the cockpit MFD
- Laser designator and IR tracker sensors removed
- Tornado G.R. Mk. 1, Tornado IDS (IT) :
- Max G-load increased at 50% wing sweep in the positive direction by about 0.43 - 0.22 G depending on fuel and weapon load
- Max G-load increased at 100% wing sweep in the positive direction by about 0.72 - 0.37 G depending on fuel and weapon load
- Wings and horizontal stabilizer aerodynamics changed
- Aileron lift sensitivity changed
- Elevator angle multipliers and sensitivity multipliers changed
- Instructor :
- forceAdvanced : false -> true
- preciseRotStopDetection : true -> false
- Tornado IDS (all GER) :
- Max G-load increased at 50% wing sweep in the positive direction by about 0.42 - 0.22 G depending on fuel and weapon load
- Max G-load increased at 100% wing sweep in the positive direction by about 0.70 - 0.36 G depending on fuel and weapon load
- Wings and horizontal stabilizer aerodynamics changed
- Aileron lift sensitivity changed
- Elevator angle multipliers and sensitivity multipliers changed
- Instructor :
- forceAdvanced : false -> true
- preciseRotStopDetection : true -> false
- Wirraway : VNE : 437 -> 580 km/h
- Yak-141 :
- Wing span : 10 -> 10.2 m
- Inner wing area : 5.12 -> 5.62 m2
- Wings with raised flaps :
- Oswald efficiency number : 0.71 -> 0.79
- Aerodynamics changed, drag increased
- Wings with full flaps :
- Oswald efficiency number : 0.7 -> 0.76
- Aerodynamics changed
- Fuselage and vertical stabilizer aerodynamics changed, drag increased
- Horizontal stabilizer :
- Span : 5.13 -> 6.2 m
- Area : 6.2 -> 0.01 m2
- Elevator area : 0.01 -> 6.2 m2
- Aerodynamics changed
- Elevator angle multipliers changed
- Afterburner thrust multiplier increased at 10 km 1400+ km/h TAS
- Afterburner thrust multiplier increased at 12 km 1800+ km/h TAS
- Water temperatures increased for RPM > 7300
- New Sensors :
- A "1RL33" track radar for the MANPADS exoskeleton, but it's that only in name, as it only has 90° search and IRST track, with less range and power)
- Another IR tracker, a modified version of the one used in targeting pods, with half the vertical range (for the UAV Raven's Eye)
- New artillery : 155 mm M777 with high-precision shells
- New "Tanks" :
- Assault (US and USSR)
- Antitank (US and USSR)
- AA Gunner (US and USSR)
- Sniper (US and USSR)
- 9A35M2 Strela-10M2 : New Skins :
- Deforming tricolor camouflage
- Late desert camouflage
- New Ground Weapons :
- 8.6 mm MG338 machine gun
- 12.7 mm 6P51 machine gun
- 21 mm smoke grenade launcher with 3D27 grenades
- 30 mm 2A72S semi-automatic sniper cannon (copy-paste XM914A)
- 30 mm XM914A semi-automatic sniper cannon
- 43 mm GM-93P under-barrel grenade launcher with VK-94 grenades
- 9M115M
- 9M133M6 (9M133 with 1600 mm penetration instead of 1200 mm)
- 9M336M1 (9M336 (which is a 9M39V copy itself) with the following differences :
- Warm-up time : 5 -> 1.5 sec
- Uncaged seeker
- FoV : 2 -> 0.75°
- Inner FoV : 1 -> 0.5°
- Gimbal limit : 38 -> 8°
- Can lock ground targets
- Guidance delay : 0.5 -> 0 sec
- Lofts
- Has 400 mm HEAT penetration)
- APILAS
- FIM-92X (FIM-92E with the following differences :
- Warm-up time : 4 -> 1.5 sec
- FoV : 3 -> 0.75°
- Can lock ground targets
- Guidance delay : 0.5 -> 0 sec
- Lofts
- Has 400 mm HEAT penetration)
- RPG-28
- Spike-SR4
- Spike-SR4ME
- TOW-2N (copy-paste TOW-2A)
- New UI icons :
- bullet_cannon_black : https://i.imgur.com/4G6QTkU.png
- bullet_cannon_red_blue : https://i.imgur.com/zMq0MQs.png
- bullet_cannon_red_blue_green : https://i.imgur.com/qdpnqi8.png
- bullet_gun_black : https://i.imgur.com/65yUDz1.png
- bullet_gun_red_blue : https://i.imgur.com/fuifXYQ.png
- bullet_gun_red_blue_green : https://i.imgur.com/j3t5rr5.png
- exoskelet_grenade_launcher : https://i.imgur.com/EKDOkIh.png
- exoskelet_jump : https://i.imgur.com/nMkQFmT.png
- exoskelet_machinegun : https://i.imgur.com/KbnFVfs.png
- exoskelet_run : https://i.imgur.com/kTCF22k.png
- exoskelet_sight : https://i.imgur.com/ltFIW5o.png
- quadrotor_hovering : https://i.imgur.com/qOIxwc3.png
- quadrotor_streak : https://i.imgur.com/byZPBzG.png
- supportplane_to_exoskelet : https://i.imgur.com/aDqsKah.png
- New tech-tree icons :
- UAV Raven's Eye : https://i.imgur.com/3AP4RvM.png
- Assault : https://i.imgur.com/x6w6G63.png
- New tank decorations :
- Grenade launcher : https://i.imgur.com/2PGIkRK.png
- 8-mm machine gun : https://i.imgur.com/So7N48T.png
- Quadcopter (black) : https://i.imgur.com/6BRa2Hb.png
- Tactical Helmet : https://i.imgur.com/S0fOwDi.png
- Cannibal Axe, Ceremonial Kris, Chainsaw, Slasher’s Hatchet, Slasher’s Mask decorations : No longer hidden, now have Marketplace links
- "SDI Forces - Harpy" badge, "SDI Forces - Hydra" badge, "SDI Forces - Minotaur" badge, TailSpin decals : No longer hidden, now have Marketplace links
- Added some of the groundwork for the crafting event
- Nevada (BB-36), Pr. 204, Terra Nova (DDE 259) : Added back the ability to skip researching them, for some reason?
- Typhoon F.B. Mk. Ib : No longer hidden, it can be bought for 1930 GE (Royal Air Force Day)
- New Vehicles :
- UAV Raven's Eye (US) :
- Hidden
- Rank 7
- BR : 10.7
- Repair Cost : 4860 / 4860 / 4860 SL
- Assault (US) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- Antitank (US) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- AA Gunner (US) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- Sniper (US) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- Assault (USSR) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- Antitank (USSR) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- AA Gunner (USSR) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- Sniper (USSR) :
- Hidden
- Rank 7
- BR : 11.3
- Stock Repair Cost : 8050 / 7310 / 8810 SL
- UAV Raven's Eye (US) :
- Increased the hangar repair time of all ground vehicles. (don't worry, it's reverted next update)
- Added new HUD and controls for the exoskeletons
- New avatars :
- Gerard Roope : https://i.imgur.com/JrBa8mh.png
- During World War II Gerard Roope, commander of HMS Glowworm, was the first to perform a heroic deed deserving of a Victoria Cross, the highest military award of the British forces. On April 8th, 1940, near the coast of Norway Glowworm found itself outgunned against the German heavy cruiser Admiral Hipper. Heavily damaged Glowworm rammed the enemy ship, piercing her hull, and fired a last shot before capsizing. Gerard Roope perished helping the crew escape the sinking ship. Hellmuth Heye, commander of the Admiral Hipper, was so impressed by Roope's actions that he wrote a letter to the British authorities recommending him for an award.
- Mobile Warrior : https://i.imgur.com/sSW6Vwh.png
- Soldier of a special detachment of mobile infantry
- Gerard Roope : https://i.imgur.com/JrBa8mh.png
- New control texts :
- "Lack of oxygen" (a WTM text ported over, curious)
- "Infantryman aiming (X-axis)"
- "Infantryman aiming (Y-axis)"
- "View in battle - Infantry (X-axis)"
- "View in battle - Infantry (Y-axis)"
- "Movement"
- "Infantryman"
- "Move axis"
- "Strafe axis"
- "Jump"
- "Fast run"
- New loading tips :
- "To use the surveillance aircraft, press {{ID_START_SUPPORT_PLANE_SHIP}}, rotate the catapult and press {{ID_START_SUPPORT_PLANE_SHIP}} again"
- "To activate the tracking camera, press {{ID_FIRE_GM}} after the shot"
- "To show the control help list, press {{ID_HELP}}"
- "In the menu, you can turn a single button fire with main and auxiliary guns: main caliber fires first, then auxiliary by another press."
- "For switching between the ship and surveillance aircraft press {{ID_START_SUPPORT_PLANE_SHIP}}"
- "For enabling surveillance aircraft flying in orbit press {{ID_SUPPORT_PLANE_ORBITING_SHIP}}"
- New mission objective text for newbie [Ground Strike] : "Destroy the enemy planes"
- New PC UI text : "32-bit version of the game is not supported."
- New vehicle names : The names of the aforementioned new vehicles
- Vehicles renamed :
- T-55M (SWE), T-72M1 (SWE) : Added a Finnish roundel
- Bf 109 F-4 (IT), Bf 109 G-2 (IT), Bf 110 G-4 (IT), Toldi IIa, Turán II, Zrínyi I (Sorozatvető) : Added a Hungarian roundel
- "HMS Nepal" -> "HMAS Nepal"
- New engine and transmission names :
- "MT-883" (previously it was only in Belorussian, French, Hungarian, Russian and Ukrainian localisations for some reason)
- "HSWL 295" (previously it was only in Belorussian, French, Hungarian, Russian and Ukrainian localisations for some reason)
- New weapon texts :
- The names of the aforementioned new weapons
- "8.6 mm machine gun shell rack filled with %s bullets"
- "30 mm ZPZ02 cannon" (Nothing uses it, IRL used on Chinese IFVs, crafting event reward?)
- New weapon type texts (for unlock conditions) :
- "Unguided bomb"
- "Guided bomb"
- New maps : (all three are used in the Mobile Infantry event)
- [Domination] modern_city
- [Domination] north_town
- [Domination] soviet_town
- [Historical Campaign] Counterattack :
- Enterprise (CV-6) : module HP : 18000 -> 7500
- Player's and their squad's armament : Type 91 Kai 2 -> Type 91 Kai 3
- Player's squad's size : 4 -> 6 aircraft
- [Single Player] The Hardest Day :
- Player's spawn moved
- Player's squad's size : 2 -> 4
- Added 2 AI Spitfire Mk. Ia
- Waypoints and radar area moved
- [Single Player] Blind Hunt :
- Airfield moved
- Airfield width : 80 -> 120 m
- [Single Player] Storm Warning :
- The player's and their squad's MiG-15bis now have Airframe, Compressor, Cover, Engine, Fuselage repair, G-suit and New boosters modifications
- Enemy scout aircraft : F-86A-5 -> F-84G, spawn moved
- Waypoints moved
- [Single Player] Airfield Under Attack :
- Airfield moved
- Airfield width : 80 -> 120 m
- Player's and their squad's Me 262 A-1a now have Airframe, Compressor, Cover, Engine and Fuselage repair modifications
- Player's squad's size : 4 -> 2
- Enemy Spitfire F. Mk. XVI (e) (CW) spawn moved, their number lowered : 16 -> 8
- [Single Player] Operation Husky :
- Player's spawn moved
- Initial Bf 109 F-4 wave : 10 -> 6
- Third Bf 109 F-4 wave : 8 -> 6
- Ship spawns moved
- 4x low quality Sims (DD-409) -> 4x high quality Churchill (I 45)
- 1x low quality Sims (DD-409) -> 1x Leander (75)
- Number of LCVPs : 20 -> 24
- Added 4x Liberty cargo ships
- Added 13x bunkers
- [Single Player] Don't throw the friends :
- Player's spawn moved
- Player's and their squad's CR.42bis now have Cover and Fuselage repair modifications
- Enemy I-15 (SGR-1820) spawns moved
- Ship spawns moved
- Added 2 fishing boats
- New statcard images :
- UAV Raven's Eye : https://i.imgur.com/rXooyYN.png
- Assault : https://i.imgur.com/R8vFd7M.png
Current Live version : 2.25.1.23
2023.04.01 10:02 TherapyJournal Overcoming Codependency: How to Improve Mental Health and Develop Healthy Boundaries
Codependency is a term that is often used to describe a pattern of behaviors and thoughts that stem from an unhealthy focus on the needs and feelings of others, often to the detriment of one's own well-being. This pattern of behavior can manifest in a variety of ways, including an excessive need for approval, an inability to set boundaries, and a tendency to put the needs of others before one's own.Codependency can have a negative impact on mental health in a number of ways. For example, individuals who are codependent may experience high levels of anxiety and stress as they try to meet the needs of others, and may have difficulty establishing and maintaining healthy relationships. They may also struggle with low self-esteem and a lack of self-worth, as they may feel that their own needs and feelings are not as important as those of others.If you are struggling with codependency, it is important to recognize that it is a learned behavior and that it is possible to overcome and grow from it. Here are some steps that may be helpful in overcoming codependency:
If you would like some assistance on your therapeutic journey click here.
submitted by TherapyJournal to TherapyJournal [link] [comments]
- Seek support: It can be helpful to work with a therapist or join a support group for individuals who are struggling with codependency. These resources can provide a safe and supportive environment in which to explore and address your codependent tendencies.
- Practice self-care: Make sure to take care of your own needs, including your physical, emotional, and psychological well-being. This may involve setting boundaries with others, learning to say no, and taking time for yourself.
- Develop a sense of self: Work on building your self-esteem and self-worth by focusing on your strengths and accomplishments. This may involve learning to identify and express your own needs and wants, and learning to advocate for yourself.
- Learn to set boundaries: It is important to establish and maintain healthy boundaries in relationships, both with others and with yourself. This may involve learning to say no when appropriate and setting limits on the time and energy you invest in others.
If you would like some assistance on your therapeutic journey click here.
2023.04.01 09:26 sodomy 35 [M4F] Georgetown/Washington DC/Surrounding areas - Dominant Social Chameleon ISO stimuli
An author's note: Please read this post in it's entirety before you message me, I've added a follow up to answer most of the basic questions I've been asked over the last 3 years since I started posting my AD.All my previous iterations were mostly about what role I could fulfill; and while this mostly still is true, walking amongst the elites the last week has opened my eyes... I'm looking for a complacent trophy to put on full display. Arriving to this city I already had a deep... Passion for power, governance; and just over all domination -- Washington DC fulfills my lust, and thirst for both political power, and monetary gain. Now I want, not need an adequate toy to share this experience with. Before I was playing conservatively; not anymore,
I've allowed my ego to rampant and on auto-pilot; thus far everything is according to design.
I'm as amoral as they come; I will eviscerate my way to the top of the governmental, and corporate ladder(s). I'm a retired hacker that has realized my full potential is being squandered away, so I'll begin to kick in the doors of 3 letter agencies until recruit me; or I die trying.
I've come to the conclusion that you need to make an impression with these sort of things, so I'm going to just let my words flow freely. So here we go:
Basics:
Height: 5'7
Weight: 175, could stand to lose a few lbs to get my abs back.
Eyes: Brown eyes.
Hair: Long curly brown hair (think Slash Rose's illegitimate son.)
Race: White.
Ethnicity: Hispanic (Cuban.)
Languages: Spanish, English, Sign-language.
Profession: Network Engineer in NW DC.
Religion: Agnostic.
A little about me:
I like long walks on the beach, sunsets, oh did I mention that I'm a sadist, and that I'm utterly insane?
I've been called a silver tongued devil; Quick witted, charismatic, with just the right amount of sarcasm.
Hobbies: Not being bored, it's a lot harder than it sounds. I enjoy learning/conversing about The Universe/space, science, and technology. I was quite nomadic in my 20s, having visited two different countries, lived in over 17 states, visited over 38.
Music: I'm more of a rhythm of the beat type of person vs. lyrics, but generally I've found myself to enjoy electronica. Definitely like a lot 80s synth pop, but again, this is just the preference, not really against the rest of the genres.
Shows: Billions, Game of Thrones, Breaking Bad, Board Walk Empire, Billions, Rome, Deadwood, Halt and Catch Fire, The Sopranos, South Park, Mad Men, Dexter,
Movies: Beetlejuice, Brain Scan, Dr. Strangelove or: How I Learned to Stop Worrying and Love the Bomb,
"What are you looking for?"
Well I can encompass a Master, a Dominant, or a Daddy, so it's really what can I provide for you?1
"How is such a thing possible?" Antisocial Personality Disorder (3.4 for those interested.)
"Why was it necessary to mention that?" To give credence as to how I can, and have been all aspects of Dominance.
"Monogamy or polyamory?" Favoritism towards polyamory, but seeing as it's rare to find multiple partners that allow me to explore my more sadistic side without tension, and/or drama, I'd go with monogamy if the individual allowed me to be depraved.
Preference in the following order: Slave, submissive, little (I will explain further below.)
Kinks: Sadism, TPE, CNC, bondage, degradation, humiliation, knife play, rope play, rape/abduction play, choking, impact play, spanking, hair pulling (I think you get the idea by now, there are still far more, here's a more comprehensive list.)
Experience: 15+ years.
Now that I've written a fucking novel about myself, let's get to you....
Age: I prefer them younger (18+) , but have dated women as old as 45; generally if I find you attractive, I won't care.
Height: the shorter the better, but I've dated women taller than myself, not a deal breaker.
Weight: I'd like someone on the smaller side, a few extra pounds will be acceptable, but no one overweight please, just not my thing.
I will list things below in order of preference, not necessarily a disqualifier. (This is only opinion, not a rating system.)
Race: White, but as long as I'm attracted I won't care, I don't discriminate.
Ethnicity: N/A read above.
Language(s): The more the merrier, accents are a huge plus, whether a southern drawl, or other.
Religion: I'm completely open to allowing you to practice whatever you'd like, just don't expect me to participate; I can be respectful of your beliefs, as long as you're respectful of mine, I am a man of science, The Universe is my religion (so to speak.)
Eyes: Blue, green, hazel, brown (If you have Heterochromia iridum you move to the front of the line, I like mutations.)
Hair: The longer the better, no preference as to style, as for color: I prefer true blondes, redheads, dirty blondes, and then brown.
Tattoos: Sure, whatever, as long as it's not overwhelming or flat out tacky, in this day in age it's harder to find someone with none, so as the trend follows above.
Piercings: Depends, some people can pull off septum piercings, but I personally dislike them, so if it compliments your facial features, sure why not. But there is definitely a breaking point where it becomes overwhelming and you just look like Hellraiser.
Education: Strong preference towards educated women, this does not necessarily mean academics, open to all.
Profession: No preference, but I do tend to like women in psychology (I have my reasons.)
Personality: If I have to learn "your" pronouns, or apologize for my "white male privilege" you can fuck right off; I don't care about politics.
Children: Strong preference in favor of not having them, unless we never intend to meet, or you don't expect a level of commitment from me to them, then I don't readily care, non-factor. To explain a tad bit, it isn't that I can't, I just would rather not raise children, I have too many plans in life that children would derail, maybe later.
If you're interested in communicating further, I prefer talking on these platforms and in this order: Discord, WhatsApp, Reddit Chat\, Skype, Kik,* open to other forms of contact.
\Reddit Chat isn't the same thing as their mailing system, just an FYI.*
Go ahead and shoot me a message, I'm waiting.
An update:
Well just to filter some things out, since I get this so many times... I will not be putting a big editorial process to this update(I say this now, after already re-reading, and editing a minimum of 5 times; I'm a slave to my own perfectionism,) so if you mostly have questions about me, ASPD, and things of the like, read this before you message me.
While I absolute love to talk about myself because I'm just such a narcissistic-hedonist, I also do get bored of repeating myself, even if it is a new person. As such read everything in it's entirety before you message me, as I'm going to entertain less, and less messages about me, and not what I'm seeking, I'd rather focus on only replying to potential partners, and absolutely nothing else, that being said if anything I have not covered in this update, or post still burns an answer from you, by all means message me.
"Were you formally diagnosed?"
I get asked about this A LOT, I'm not going to go into very many details, suffice it to say, yes, but it's been labeled as a misdiagnosis, all you need to know is I score high, and I do the things you'd expect, the pyromania, the violence that is actually associated at early age, the works, I'm not comfortable giving you more beyond that, and I will not be entertaining questions about my personal life, maybe a partner could ask me those questions, but I'm not letting you in my head, that's my game, not the other way around :).
Please do your own research beyond this point, it's borderline laziness how often I keep getting asked about this.
"Why are you so open about it(ASPD)?"
Isn't it obvious? A lot of you can't fathom why someone with ASPD would just openly come out, and admit to people, well I guess I really should've brushed up on this when I first made my post, or at least go into a far more descriptive detail than I had originally, so here goes:
If I'm ever to lead a sort of a long term relationship based on trust, and honesty, just how in the HELL do you expect me to explain this to you ever so casually? It's best to show your cards in the beginning, this is my own baggage, or some form there of.
There's two reasons I'm choosing to do this online, and vehemently under anonymity; 99% of you will be irrelevant to me, 99% of you will never meet me, it's just that simple, ergo why wouldn't I just preface my entire description as such, and as brutally honest as possible? Secondly I do not want a partner whom I need to continue to wear a mask for, I want to be me, the real me, the good, the bad, and the ugly.
What I find the most is women that fetishize the entire ordeal, that's all fine and dandy, but it does show just a lack of understanding about what APSD is as a whole, and to be perfectly blunt, you're wasting my time, I don't need to feed into your lonely thrill romance you spun in your head from watching true crime dramas. More often than not, this what happens, spare us the role-playing, I'm just not that bored.
"Empathy"
One clear distinction I'd like to make, so I can stop getting asked about it, we DO have empathy, it's just not how YOU experience empathy. Think of a light switch, by default most of the population's is on, ours is off by default, and furthermore we have the ability to turn it on, and off. Yes, it is that simple, yes we use it for manipulation, now stop asking me about this, it's boring to repeat this.
"Emotions"
Boredom, rage. This is what I'm capable of in the dark, empathy off. I'm constantly seeking stimuli, if you notice by actually looking through my posts, I've moved a ton of times, and always national parks... New atmosphere, new adventures, new dangers, you know, the shit that gets your heart pumping, adrenaline. This is my favorite drug, this is the high I constantly chase to kill the boredom. Rage is just self explanatory, my defaults are animalistic.
I am fully capable of experiencing all emotions, it's just for the most part, because I don't want do, I don't allow myself to.
"Manipulation"
For the longest time I told myself who cares if I burn bridges in my wake, I'm building a highway in its place. Mostly still true, and I absolutely use it on a daily basis for survival, I must stress, and emphasize survival, here is why; I'm human, like the rest of you, what do you do on a daily basis, if not find means, and ways to survive, and entertain yourself? I know no other way other than to use people to my advantage, I minimize the damage where I can, and move about my daily existence, guilt, and worry free about doing any wrong, an argument could be made that we all use each other in some weight, or capacity, and that's good enough for me.
I'm sure by now you're probably wondering what the hell any of that has to do with anything, it's simple if the point flew over your head, again. I'm tired of manipulating people, using them, abusing them, discarding them, I didn't grow a conscious I'm not "growing" as a person, but much more likely, I'm just bored of the routine, or the process, which has become the symphony of my life.
"Love"
I by no means ever want to experience this love you all chase like Alice clumsily falling down the rabbit hole. I've seen it so much in my life it's downright pathetic, and I actually feel bad for those of you that have such strong emotions, see empaths. You're slaves to these emotions, you let people use and manipulate you, you've been hurt, and had your heart ripped from your chest, and it feels like you no longer have purpose, lacking direction, and meaning in life. I merely know this from generally observing humans for most of my natural born life. I'm more than happy to remain the way I have always been, and never wish to experience emotions in the way you do, I find it to be an advantage, one I can apply to more important things in life, like the pursuit of knowledge.
I hope the psych nerds will now stop asking me these questions, I've paid my dues.
"Preferences"
My preferences, are just that, a list of my preferences, at no point in any of my writing did I say I was prejudice between one thing, or that I show favoritism. I merely made a chart listing some of the attributes that I myself, personally find to be significant to me, but that isn't to say, or detract from other things. It's the equivalent of asking me if I prefer Metallica, or Megadeth; well I'm going to say I prefer one over the other, but I enjoy both, and the genre as a whole, the genre being women in this case. I enjoy women for my own personal entertainment, and amusement -- which makes it all the more hilarious to me when I get called a misogynist.
so please spare me all your comments, and messages telling me that it's so "intimidating", if my post intimidates you, what can I really even begin to say about that? It doesn't sound like we'd be compatible, or much less you'd be able to accept me as a person, in any case this is a personal issue.
"You Need Help!"
I know what the help is, they just remind you repeatedly that your actions have consequences, they do not prescribe a medication for this, just therapy, and I know enough already to check myself, it really is that easy.
P.S:
"To My Adoring Fans"
You call me an edge-lord, cringe, and a wide range of inane insults, that truly don't phase me, since I get a lot of these messages, I thought I'd give you my rebuttal; just so you know I sleep naked so that anyone that doesn't like me, can kiss my ass - feel free to visit anytime!
P.S.S: I now operate, function, and walk amongst the elite of the nation; I see my kind everywhere, this is what Rome must of felt like in it's heyday; Cicero you clever bastard... I bid you all adieu -- and depart with this:
{"Το σύμπαν είναι αλλαγή. η ζωή μας είναι αυτό που την κάνουν οι σκέψεις μας.";}
Sincerely,
<~sodomy>
2023.04.01 09:22 valeriantincture My cat won't let me sleep and I feel like I've tried almost everything? Seeking advice
My cat is a bit over two years old and I've had her since she was six months. About a year ago, we moved into a small one bedroom apartment together and I began working and studying full time. I made extra care to pay more attention to her and keep her stimulated during this change in environment and routine. It's been a year now, and as part of my studies I'm having to spend long hours out of the house on a placement. During placement time (both this year and last) she has become extremely demanding at nighttime. She's a bit of a handful in the evening when I'm going through less busy periods, but she gets a lot more intense around these times and I suspect it's to do with me not being home. She will start yowling very loudly as soon as I get into bed, and will continue no matter what I do. I'm 90% sure she's yowling because she wants to play. If she stops, she'll generally start again at 3am and then again at 5am and 6. This is loud and impossible to sleep through. She'll often also scratch at the wood on my bedframe, pounce on me and repeatedly boof me with her head (cute but not at 5am!). I know cats are crepuscular sleepers, so some of this is natural, but it's really impacting me.
Things I have tried or am currently doing:
-I play with her for 30-45 minutes every day. Usually 10-15 when I get home, and then 20-30 before I go to bed. I feed her after this last play. It seems like she just wants more playtime than this, so I could try upping it?
-I shut the door when she yowls at night. However, she scratches (again - for hours!) when I do this, and it makes sleep impossible. I'm also in a rental and afraid of damage to the door
-I have a lot of toys and cat enrichment activities which I swap out/rotate often so she doesn't get bored when I'm out, but I'm not sure if she's engaging with them.
-I do my best to ignore her when she yowls at night, but she can honestly go on for hours sometimes and it's difficult, especially when I'm exhausted and have a 6am start the next day. But generally I just don't respond to her yowling at all in case it incentivises things
-I've eventually tried to resort to the spray bottle technique when she yowls. I really didn't want to do this as I know there's conflicting evidence as to whether this is fair for cats, but I'm at the end of my tether so I've given it a go. I spray her if she yowls in my room at night. This doesn't seem to have any effect on her? It actually seems like she thinks it's a game. She won't flinch at all if sprayed and will just continue yowling.
-I've tried giving her some supervised outdoor time for extra enrichment. She broke out of the cat harness when I tried her with one. Without a harness, she got into such intense fights with my neighbours' cats that it actually caused conflict between myself and my neighbours. Even when supervised, she is lightning quick - she would run into neighbours' open doors to fight their cats, and tried to get through cat doors. Several of my neighbours were really upset by her doing this as they felt that she was terrorising their cats. It just caused too much conflict to be worth it, and the situation made me very anxious as I don't want to be on bad terms with my neighbours. I didn't want to push the matter and just accepted that she needs to be indoors.
Things I am considering doing:
-Earplugs paired with white noise. I've tried earplugs on their own before but they don't seem to block the sound and she still woke me up.
-Possibly using a feliway diffuser to see if it soothes her?
-Cat TV? I don't own a tv or a projector, but I would consider getting one to keep her more stimulated when I'm out, seeing as I don't think the toys I have are doing it.
I've been really struggling with this behaviour, I love my cat a lot but it's causing tension. I am struggling with the compromised sleep, I'm so busy and under a lot of external stress and I'm not coping well. It's also causing problems in my relationship, as my partner often doesn't want to stay over. I'll be seeing a cat behaviour specialist soon because this has gone on for so long and I'm struggling, but I wanted to see if anyone else has any advice/feedback/ideas. I really want my cat to be happy, but I also want to sleep. It would mean a lot!
submitted by valeriantincture to CatAdvice [link] [comments]
Things I have tried or am currently doing:
-I play with her for 30-45 minutes every day. Usually 10-15 when I get home, and then 20-30 before I go to bed. I feed her after this last play. It seems like she just wants more playtime than this, so I could try upping it?
-I shut the door when she yowls at night. However, she scratches (again - for hours!) when I do this, and it makes sleep impossible. I'm also in a rental and afraid of damage to the door
-I have a lot of toys and cat enrichment activities which I swap out/rotate often so she doesn't get bored when I'm out, but I'm not sure if she's engaging with them.
-I do my best to ignore her when she yowls at night, but she can honestly go on for hours sometimes and it's difficult, especially when I'm exhausted and have a 6am start the next day. But generally I just don't respond to her yowling at all in case it incentivises things
-I've eventually tried to resort to the spray bottle technique when she yowls. I really didn't want to do this as I know there's conflicting evidence as to whether this is fair for cats, but I'm at the end of my tether so I've given it a go. I spray her if she yowls in my room at night. This doesn't seem to have any effect on her? It actually seems like she thinks it's a game. She won't flinch at all if sprayed and will just continue yowling.
-I've tried giving her some supervised outdoor time for extra enrichment. She broke out of the cat harness when I tried her with one. Without a harness, she got into such intense fights with my neighbours' cats that it actually caused conflict between myself and my neighbours. Even when supervised, she is lightning quick - she would run into neighbours' open doors to fight their cats, and tried to get through cat doors. Several of my neighbours were really upset by her doing this as they felt that she was terrorising their cats. It just caused too much conflict to be worth it, and the situation made me very anxious as I don't want to be on bad terms with my neighbours. I didn't want to push the matter and just accepted that she needs to be indoors.
Things I am considering doing:
-Earplugs paired with white noise. I've tried earplugs on their own before but they don't seem to block the sound and she still woke me up.
-Possibly using a feliway diffuser to see if it soothes her?
-Cat TV? I don't own a tv or a projector, but I would consider getting one to keep her more stimulated when I'm out, seeing as I don't think the toys I have are doing it.
I've been really struggling with this behaviour, I love my cat a lot but it's causing tension. I am struggling with the compromised sleep, I'm so busy and under a lot of external stress and I'm not coping well. It's also causing problems in my relationship, as my partner often doesn't want to stay over. I'll be seeing a cat behaviour specialist soon because this has gone on for so long and I'm struggling, but I wanted to see if anyone else has any advice/feedback/ideas. I really want my cat to be happy, but I also want to sleep. It would mean a lot!
2023.04.01 09:14 RumLake 29 [M4F] #EastCoast-Master looking for TPE/slave girl to own and train
I'm a 29 white male from NYC looking for a girl that serious and wants to make Masteslave dynamic a reality.
Now most of these dynamics are all a kink or secondary or come and go but I am looking for a girl that's really seeking ownership and giving yourself up as the primary goal of our relationship. A girl that's naturally submissive and is okay with leaving everything behind to start her life over with her Master.
A little about me: I am 6'1 tall, white, brown hair, brown eyes, average body type. I do have a steady WFH job that's in tech. I am looking to relocate soon so distance or location is not an issue for me. I am capable of taking care of you and our future family without an issue. You will not have to work ever again and I will take care of us financially. I am naturally dominant and naturally submissive girls go well with me. I am also very loyal and caring to the right girl. You as my slave will also be my girlfriend, and wife one day. Once I find the right girl you will have my word and I will always be by your side no matter what. I will never cheat or lie to you. I give my girl my very all and work through every problem together. I am also sadistic and enjoy masochist girls as well. Some other kinks I enjoy: Anal, impact play, rough sex, TPE, edging, denial, forced orgasms.
If you're interested we can start off online of course with future plans to live together one day. Starting off with online you will have to message throughout the day and be good at responding. Depending on what your job/life situation is we can adjust it don't worry. I will control your day to day activities. What you wear, when you wake up, who you see, control of what apps you're allowed to use, the foods you eat, everything I decide essentially. I know its a lot off the jump so we can start off small and work our way up. I don't expect a girl to do this all in the beginning without getting to know me well and I am okay with that. As long as the girl is eager and wanting this life style just as much as I am.
If you're serious and want this, send me a chat message and let's get to talking. Send me a chat message with your name, age, ethnicity, and a general description of yourself. See you there!
submitted by RumLake to AgeGapPersonals [link] [comments]
Now most of these dynamics are all a kink or secondary or come and go but I am looking for a girl that's really seeking ownership and giving yourself up as the primary goal of our relationship. A girl that's naturally submissive and is okay with leaving everything behind to start her life over with her Master.
A little about me: I am 6'1 tall, white, brown hair, brown eyes, average body type. I do have a steady WFH job that's in tech. I am looking to relocate soon so distance or location is not an issue for me. I am capable of taking care of you and our future family without an issue. You will not have to work ever again and I will take care of us financially. I am naturally dominant and naturally submissive girls go well with me. I am also very loyal and caring to the right girl. You as my slave will also be my girlfriend, and wife one day. Once I find the right girl you will have my word and I will always be by your side no matter what. I will never cheat or lie to you. I give my girl my very all and work through every problem together. I am also sadistic and enjoy masochist girls as well. Some other kinks I enjoy: Anal, impact play, rough sex, TPE, edging, denial, forced orgasms.
If you're interested we can start off online of course with future plans to live together one day. Starting off with online you will have to message throughout the day and be good at responding. Depending on what your job/life situation is we can adjust it don't worry. I will control your day to day activities. What you wear, when you wake up, who you see, control of what apps you're allowed to use, the foods you eat, everything I decide essentially. I know its a lot off the jump so we can start off small and work our way up. I don't expect a girl to do this all in the beginning without getting to know me well and I am okay with that. As long as the girl is eager and wanting this life style just as much as I am.
If you're serious and want this, send me a chat message and let's get to talking. Send me a chat message with your name, age, ethnicity, and a general description of yourself. See you there!
2023.04.01 09:13 LeeCloud27 Touhou: Living on From Another (Part 1)
You felt pain. Pain all over your body, on your skin, in your muscles, your bones. You felt your skull bashed; cracked like a chicken egg. The feeling of an immense force of impact had lingered on in you for quite a long period of time.
You felt deaf. Your eardrums have rung so loud as though a million bells clanged against each other all at once. It was so loud that they popped like a bubble, bursting open into an irreparable state.You smelled blood. Your nose was dry and normal like any other nose. But when it happened, the strong scent of warm iron quickly filled up the nostrils both in and out, replacing the breath of air you had breathed in moments ago.
You couldn’t taste. Your tongue which had nothing to taste now could no longer taste anything, because you had bitten so hard into it that it flew out, never to be reattached ever again.
Touch, hearing, scent, taste, all of these senses failed you when you needed them all most. Except for sight.
You could still see. You could see as clear as the ground beside your skin. You could see the pool of blood that began to increase in area, the sight of people all around you panicking, unsure on what to do in such a case. You could see the silver reflection of yourself from the truck that had its front stained in red. You could see your cracked phone, the screen remained on while the video of your favorite Touhou song had continued to play.
But you could no longer hear it, and soon, you may no longer see. Your vision begins to darken, your mind still unable to come together on what exactly happened, yet deep within, you begged, pleaded, prayed to whatever god or high being still existed at this very moment.
You didn’t want to die, not yet. Not in such a state. But that’s not how life works does it? And soon, even your sight had failed you.
…
…
…
You wake up.
You find yourself lying on a cold hard ground, the moist scent of rainfall filling your lungs, the sound of brimming silence, the taste of your own saliva. And as you open your eyes, all you could see is darkness, yet the sight of a dim light not too far away.
You raise your head up, standing with your knees. You could walk, you didn’t limp or struggle, you walked just how you did before. You could move your body in any way and there was nothing to keep you from doing so.
Each step you took, an echoing noise took its place shortly after. You didn’t know where you were, or where to go. You had no idea how you got here, why you were here to begin with. But standing around and doing nothing would solve nothing, so you walked.
Seconds upon seconds, upon minutes, upon hours, days, weeks, months, years, decades, centuries…
You did nothing but walk, and still no end to this strange void you stumbled upon. You already forgot why you were here in the first place, how you got here. You forgot your own name, your identity, your personal favorite things. You were a husk, a hollow shell of a being you’re not even sure if you could consider human by now.
You didn’t need to eat, or drink, or breathe. You didn’t need to think, or smell, or listen. You didn’t even need to use your eyes, or feel your surroundings. Your senses were no longer of use. Yet you still kept on walking.
Until…You arrive somewhere. Something different.
It was faint, you had a hard time seeing it due to your eyes having lost all function other than to stare forward. A part of you almost considered the sight to be some kind of hallucination that your mind conjured up as a desperate attempt to feel something again after spending an eternity walking.
The closer you got, the more the sight revealed itself. It looked small, resembling a small slit entryway to something other than the dark endless void. You could see eyes staring out, gazing upon you intently. You didn’t care though, all you cared about was getting close.
You reached the spot, and decided to stick your head inside the hole. The entire interior was filled with eyes that covered every spot within your vision. Some stared at you, others looked elsewhere, but you could see them so could they.
Then you felt something, a warm, strong feeling on your hand. It was something you hadn’t felt before in ages, enough so that you were brought to shock. But your mind couldn’t even be given a second to think about it before you were pulled right into the gap.
You were falling, falling fast and hard. The sound of wind filled your ears, a sound you thought had long been forgotten. Another sound then came by, speaking in a language you almost forgot about.
“Well, what do we have here?” The voice said in an alluring tone. “I never imagined I would find a human wandering around here all by themselves… But then again, judging by how you look, you’re not a human anymore, are you?”
You didn’t know who or where this voice came from, questions began to fill your mind up, the tip of your tongue struggling to move in order to form words.
“Fufufu…Don’t force yourself, dear. After all, where I’ll be taking you will be much different from what you had experienced before in the past. Nothing like a particular universe still struggling with its own problems.”
You didn’t understand, it seemed as though they were referring to something, yet you don’t have any reason to think too hard about it.
“Well, anyway. I’m here to give you another chance. However, it’s going to be a little different compared to before. Your body and spirit have decayed to a point where you are completely unrecognizable, impossible to repair to a newer state without disregarding what made you you. So instead, I’ll be giving you a different kind of option.
*snap*
Six different objects of similar size and material formed around you. Each one had a different frame, but they all showed different reflections, reflections of people you never thought you would see ever again.
“Be sure to choose one, as you will experience the life they have, the memories they bear, the skills they honed. You will act like them, think like them, live life as them. This may look like a Choosing of Your Adventure. But if I had to describe it as something different… You are meekly Living on From Another.”
“Choose Wisely, fellow Gensokyian.”
View Poll
2023.04.01 09:00 dspeyer EA Forum Digest 01 Apr 2023
Newcomb's Paradox Explained
There are two decision theories: causal and evidential, which often agree in normal cases but disagree in weird ones, e.g. Newcomb's paradox, so the paradox teases out our competing intuitions on how to make decisions.Source: Hilary Greaves on 80k podcast
There are two boxes in front of you: a transparent one that you can see contains £1000 and an opaque box that either contains a million pounds or nothing. Your choice is to either take both boxes or just the opaque box.
The catch is that a very good predicter has predicted your decision and has acted, (based on their prediction) as follows:
13 more paragraphs...
Setup Causal decision theory Evidential decision theory Another example: smoking lesions
A Brief Argument for Rapid Movement Growth
I feel that effective altruism has been growing more slowly than is ideal and has the capacity to grow faster. I also feel that faster growth has an extremely positive best-case scenario, and a worst-case scenario that is both highly unlikely and no worse than the status quo. Finally, I feel that rapid growth is highly impactful, highly tractable, and highly neglected, even when compared to other movement-building work, and I believe that rapid growth should be a focus of EA movement-building. For now, I would like to open a possible series on the subject by presenting a simple thought-experiment that gives my intuition in favor of rapid growth. Later, I plan to address potential criticisms at length.5 more paragraphs...
[Γαμινγκ the Algorithms: Large
Language Models as Mirrors](https://forum.effectivealtruism.org/posts/KoriEzLMz5kxbHLEm/gamingk-the-algorithms-large-language-models-as-mirrors)Introduction
Algorithms are not clever in the sense that they don’t make judgments, opinions or choices of their own, they simply absorb input, combine what many others have said, treat those opinions according to set rules and spit out some output based on the input and rules (the functions that reinforce their synapses). In that sense, they have the intelligence of an amoeba, whilst it is questionable if they have the same motivation for survival as it. Survival of the fittest, as per the darwinian pop motto, is only a ‘law’ for living things – indeed I doubt whether it would’ve been sensible for the developers of Large Language Models (LLMs) to try to code for survival of the fittest, as this may have resulted in an existential threat for the whole of humanity.
14 more paragraphs...
Graphic Design is Our Passion
Attention all effective altruists!We have some exciting news to share with you all. After much consideration and analysis, we have decided to change the headings on this forum to the most effective font - Comic Sans.
Why, you may ask? Well, as avid supporters of effective altruism and its focus on cost-benefit analysis, we conducted a thorough study on the most effective font to use for our headings. And the results are in - Comic Sans came out on top!
Not only did Comic Sans score highly in terms of readability and accessibility, but it also brought a smile to the faces of our testers. And as we all know, the happiness and well-being of individuals is a key component of the utilitarianism philosophy that many effective altruists subscribe to.
3 more paragraphs...
One EA’s Perspective on Depression
I decided to post this in draft form; I plan to clean it up as needed but wanted to get it out sooner.In order to talk about depression, we need to first talk about emotions in general. Why do we have emotions? What is their purpose?
Emotions are the signals our body sends us to communicate how we are in relation to the world around us. They enable us to survive, thrive and reproduce.
Emotions can be split into two classes: lower-order and higher-order.
Lower-order are the basic, primal emotions that we share with other animals. These include fear, anger, disgust, joy, and sadness (the ones in Pixar’s Inside Out). Lower-order emotions are involuntary and usually accompanied by physiological changes in the body, such as heart rate, breathing, and muscle tension.
12 more paragraphs...
A Normal Straightforward Post
A: Knock-knock!B: Who's there?
A: Cowgo.
B: Cowgo who?
A: The past year has been a distressingly-active one, for this community. Here, of course, I'm referring to the union of the rationality community, the Effective Altruism community, and the AI alignment/DontKillEveryoneism (aka "DKE") community.
A quick timeline in case you've been in cryostasis under a rock:
April 1, 2022: MIRI, the OG AI DKE organization, announced its new "Death With Dignity" strategy. This gave the AI alignment/safety field a kick in the ass, which seems pretty good. Importantly, it also increased the percentage of the community that takes DKE seriously. Probably. Hopefully. I haven't run a survey.
26 more paragraphs...
Hooray for stepping out of the limelight
Iterating on our redesign (Forum update April 2023)
Thank you to everyone who gave us feedback on our recent redesign of the Forum! We’ve looked closely at your feedback and our findings from interviews with new users.Two clear themes emerged:
After careful consideration, we’ve decided to change our sans-serif font from Inter to Comic Sans. We believe that this friendly and distinctive font will address the concerns of both new and experienced users, and keep users engaged for longer.[1]
We’re confident that all of our users will be happy with this font change. We welcome you to contact us with your praise, or post it in the comments below.
2 more paragraphs...
We might get lucky with AGI warning shots. Let's be ready!
Book Review: Parfit - A Philosopher and His Mission to Save Morality
I recently wrote a short review of David Edmond’s forthcoming biography on Derek Parfit, which I thought might be of interest to folks here for obvious reasons.I’ve included the full post below, and more info on the book can be found here. I highly recommend it and encourage anyone interested to pick up a copy.
"It is impossible to read off a person's personality from their ideas. Discuss." One could imagine such a question in an All Souls general paper. And there are such cases where there seems to be no connection. The special theory of relativity provides no clue to Einstein's genial personality. Parifitan philosophy, however, is bound up with aspects of his character.
20 more paragraphs...
2023.04.01 08:56 azcpl121314 [NM] 4002014 LEGO HUB Birds - 100 spots at $3/ea
Item Name Set Number: (4002014) LEGO HUB Birds
Price: $282 (BE)
Shipping: $18 12x8x4 2lbs, USPS 85283 to 10021 $3 shipping materials
Raffle Total/Spots: $300 / 100 spots @ $3ea
Price justification: BE
Call spots: Y
Spot limit per person: N
Duration of spot limit: na
Location(Country): USA
Will ship international: Yes, Outside CONUS pays difference
Timestamp pics: https://imgur.com/a/pkxJlJV
Description: Iconic, Minty, hard to find set from 2014! Box is pristine and will be packed with extra care.
Payment required w/in 15 minutes of raffle filling. 10 minutes on drama spots.
CashApp payments should have NO COMMENTS. Comments will result in a permanent ban
PayPal Info: [REDACTED]
Cash App Info: [REDACTED]
Tip BlobAndHisBoy
Number of vacant slots: 75
Number of unpaid users: 6
Number of unpaid slots: 25
This slot list is created and updated by The EDC Raffle Tool by BlobAndHisBoy.
1
2 GorillaX
3 yo-Marie-yo
4
5
6
7
8 bowardboolin
9
10 bowardboolin
11 mrxscarface
12
13
14 ssj3dvp11
15 GorillaX
16
17
18
19
20 GorillaX
21 ssj3dvp11
22 GorillaX
23
24 bowardboolin
25
26
27
28 mrxscarface
29
30
31 GorillaX
32
33
34 yo-Marie-yo
35
36
37
38 ssj3dvp11
39
40 GorillaX
41
42
43
44 ssj3dvp11
45
46
47
48
49
50
51
52
53
54
55
56
57 BlobAndHisBoy
58 ssj3dvp11
59
60
61
62
63
64 GorillaX
65
66
67
68
69
70
71
72
73
74 GorillaX
75
76
77
78
79
80 GorillaX
81
82
83
84
85 GorillaX
86
87
88
89
90
91
92
93
94
95
96
97 mrxscarface
98
99 yo-Marie-yo
100
submitted by azcpl121314 to lego_raffles [link] [comments]
Price: $282 (BE)
Shipping: $18 12x8x4 2lbs, USPS 85283 to 10021 $3 shipping materials
Raffle Total/Spots: $300 / 100 spots @ $3ea
Price justification: BE
Call spots: Y
Spot limit per person: N
Duration of spot limit: na
Location(Country): USA
Will ship international: Yes, Outside CONUS pays difference
Timestamp pics: https://imgur.com/a/pkxJlJV
Description: Iconic, Minty, hard to find set from 2014! Box is pristine and will be packed with extra care.
Payment required w/in 15 minutes of raffle filling. 10 minutes on drama spots.
CashApp payments should have NO COMMENTS. Comments will result in a permanent ban
PayPal Info: [REDACTED]
Cash App Info: [REDACTED]
Tip BlobAndHisBoy
Number of vacant slots: 75
Number of unpaid users: 6
Number of unpaid slots: 25
This slot list is created and updated by The EDC Raffle Tool by BlobAndHisBoy.
1
2 GorillaX
3 yo-Marie-yo
4
5
6
7
8 bowardboolin
9
10 bowardboolin
11 mrxscarface
12
13
14 ssj3dvp11
15 GorillaX
16
17
18
19
20 GorillaX
21 ssj3dvp11
22 GorillaX
23
24 bowardboolin
25
26
27
28 mrxscarface
29
30
31 GorillaX
32
33
34 yo-Marie-yo
35
36
37
38 ssj3dvp11
39
40 GorillaX
41
42
43
44 ssj3dvp11
45
46
47
48
49
50
51
52
53
54
55
56
57 BlobAndHisBoy
58 ssj3dvp11
59
60
61
62
63
64 GorillaX
65
66
67
68
69
70
71
72
73
74 GorillaX
75
76
77
78
79
80 GorillaX
81
82
83
84
85 GorillaX
86
87
88
89
90
91
92
93
94
95
96
97 mrxscarface
98
99 yo-Marie-yo
100
2023.04.01 08:52 Bitcoinz_Tech Coinbase plans to continue operations in Canada as Binance faces possible exit amidst tightening regulations
The Canadian government has been actively working to tighten regulations for cryptocurrency exchanges to combat money laundering and terrorist financing. As a result, cryptocurrency exchanges operating in Canada are subject to more stringent rules and requirements.
Coinbase, one of the largest cryptocurrency exchanges in the world, has announced its intention to continue operating in Canada despite the regulatory changes. Coinbase has been operating in Canada since 2015 and has a significant user base in the country.
On the other hand, Binance, one of the largest cryptocurrency exchanges by trading volume, has faced increased scrutiny from regulators in multiple countries, including Canada. There have been reports suggesting that Binance could be poised to exit the Canadian market as a result of the regulatory changes.
It's important to keep in mind that regulations and rules for cryptocurrency exchanges can vary widely by country, and it's important for users to carefully consider the risks and potential regulatory impacts when choosing an exchange.
submitted by Bitcoinz_Tech to BitcoinzTech [link] [comments]
Coinbase, one of the largest cryptocurrency exchanges in the world, has announced its intention to continue operating in Canada despite the regulatory changes. Coinbase has been operating in Canada since 2015 and has a significant user base in the country.
On the other hand, Binance, one of the largest cryptocurrency exchanges by trading volume, has faced increased scrutiny from regulators in multiple countries, including Canada. There have been reports suggesting that Binance could be poised to exit the Canadian market as a result of the regulatory changes.
It's important to keep in mind that regulations and rules for cryptocurrency exchanges can vary widely by country, and it's important for users to carefully consider the risks and potential regulatory impacts when choosing an exchange.
2023.04.01 08:31 AutoModerator Announcement: Subreddit Traffic Calming Measures are now in Effect
Greetings and Happy April!
As we all know, recently, local barriers placed in Vancouver to reduce traffic speed on unsafe roads have become very popular. The moderation team of /Vancouver has carefully taken notice of the positive response from our users and supporters and in reply, we have decided to institute a new policy for the subreddit.
Moving forward, all posts will be held for manual review (otherwise known as “traffic calming”) by a moderator. We believe this change will positively impact the subreddit as we will be able to stop users from littering this subreddit with posts about negative themes like cherry blossom photos, videos of putting stuff in your car, discourse on telecoms, and dozens of identical questions in one day about which neighbourhood is the cheapest to move to while also being safe and centrally located. (Hint: it’s none of them.)
As we’re a small mod team and yet one of the largest subreddits in Canada, please note that it may take 24-48 hours for a post to be manually approved.
Thank you so much in advance for your patience and understanding.
submitted by AutoModerator to vancouver [link] [comments]
As we all know, recently, local barriers placed in Vancouver to reduce traffic speed on unsafe roads have become very popular. The moderation team of /Vancouver has carefully taken notice of the positive response from our users and supporters and in reply, we have decided to institute a new policy for the subreddit.
Moving forward, all posts will be held for manual review (otherwise known as “traffic calming”) by a moderator. We believe this change will positively impact the subreddit as we will be able to stop users from littering this subreddit with posts about negative themes like cherry blossom photos, videos of putting stuff in your car, discourse on telecoms, and dozens of identical questions in one day about which neighbourhood is the cheapest to move to while also being safe and centrally located. (Hint: it’s none of them.)
As we’re a small mod team and yet one of the largest subreddits in Canada, please note that it may take 24-48 hours for a post to be manually approved.
Thank you so much in advance for your patience and understanding.