Psu nso task list

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:
​

1. 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.
2. 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.
3. 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.
4. 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.
5. 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.
6. 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.
7. 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.

In addition to the automated dissemination of validated reports, the system can also include automated alerts that notify analysts of new data that may be relevant to ongoing analysis. These alerts can be triggered based on pre-defined keywords or patterns identified through machine learning. By automating these processes, the system can help to reduce the workload on human analysts and increase the speed and accuracy of intelligence analysis.
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:
​

1. 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.
2. 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.
3. 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.
4. 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.
5. 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.
6. 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.
7. 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.

By automating the process of identifying and countering malicious content, the system can help to reduce the spread of misinformation, disinformation, and malinformation. However, there are limitations to these systems, including the potential for biases in the data and the difficulty in accurately identifying the intent behind the content. Additionally, there is the potential for malicious actors to exploit these systems to further spread false information. Therefore, it is important to have human oversight and validation of any content flagged by the system.
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

When I began my career in recruiting, I became intimately familiar with the applicant’s journey through the job application funnel, from the moment they submitted their application to the moment they were either offered the role or turned down.
I moved to consulting because I felt I could do more good working alongside applicants instead of being on the other side of the table.
Over the course of my consulting career (going on 12 years now!), I’ve helped hundreds of clients overcome various challenges involved in all aspects of the job search process, including:
✅ Writing a compelling resume
✅ Switching industries
✅ Troubleshooting ineffective resumes
✅ Troubleshooting broken job searches
Today, I’m going to cover three key stages in the job search process, what typically goes wrong with them, and solutions. These stages are:

• The online application
• The phone screen
• The job interview

The online application

Symptoms that your application process is broken
If your callback rate is less than 10% (as in, less you receive callbacks on less than 1 in every 10 job applications), then chances are there’s something wrong, assuming you’re applying to jobs you’re 60 to 70% qualified for.
Keep in mind this number varies by industry, role, location, and economic conditions.
​

❝ If your callback rate is less than 10%…then chances are there’s something wrong…

​
Why?

• Your resume may not be targeted enough to the job you're applying for
• The content may not speak to the needs of the recruiteposition,
• It may not be clearly written, or
• It may read like a job description rather than being results-oriented.
• You’re using formatting that interferes with the ability of some applicant tracking systems to parse your resume.

How you fix it
At this stage, your resume is most likely the source of your problems. Assuming you’ve been qualified for the jobs you’ve applied to, take another look at your resume:

• Does it clearly tell the recruiter how you meet the qualifications of the job? In other words, is it targeted?
• Does it sound like a job description? Your resume should be unique to you, and should highlight what makes YOU an ideal match, based on your mix of skills, education, and experience (as opposed to being generic like a job description).
• If you’re a leader, does it demonstrate leadership impact?
• Does it provide quantitative and qualitative achievements? Are your actions clearly mapped to your accomplishments?
• Does it avoid the use of fluff?
• Does it avoid the use of tables, logos, headers, footers or charts?
• Is it written in a common font like Calibri or Times?
• Are there spelling or grammar errors?

Revise your resume to ensure it clearly addresses the qualifications (i.e., experience, education, and skills) listed in the job posting.

The initial recruiter screen

Symptoms that something may be wrong with your initial screens
The rate at which applicants move past the initial screen varies widely, but in my experience, you should be moving forward on every 4 in 10 applications, at the least.
If you’re not, that tells me something’s going wrong during the screen that’s causing the recruiter to not move forward with your application (which by the way could be conducted over the phone or social media platforms such as LinkedIn).
​

❝ You should be moving forward on every 4 in 10 applications…

​
Why?
There are a few areas where you may be tripping up here. A few of the key ones include:

• Your desired salary may not be within the position’s range (especially if you overshoot their salary range)
• What you say during the interview doesn’t align with what’s on your resume
• Your experience doesn’t align with the role after further review
• You exhibit a low level of enthusiasm, such as by being unprepared or not knowing enough about the company or position.
• Other warning indicators could include poor communication skills, lack of professionalism (i.e., you’re late to the interview without a valid reason), or poor listening skills

How you fix it

• Make sure your story and resume align.
• Practice your tone and exhibit professionalism in the way you speak and show up on time.
• Research the company and role beforehand, understand their market, products, services, and challenges they currently face.
• Practice common phone screen questions and research the position's salary range beforehand. Avoid revealing your desired salary too early.

The job interview

Symptoms that you’re failing your interviews
While the number of interviews vary from one company to another, many companies use three as the magic number. That means you’re going through three interviews before being offered a job.
According to recent estimates by Jobvite, the interview to offer conversion rate was about 36.2%, up from around 19% during previous years. That’s how likely you are to be offered the job.
Based on that data, a ballpark conversion rate of about 25% is probably a safe average to go by. That means you have a 1 in 4 chance of moving past each stage of the interview.
If you’re seeing results that are drastically less than this (say you’re only moving past 1 out of every 9 interviews), then you’re probably fudging the interview.
​

❝…You have a 1 in 4 chance of moving past each stage of the interview.

​
Why?

• You can’t recall your previous roles, responsibilities, or accomplishments in enough detail when hiring managers dig deeper.
• You’re not good cultural fit for the company.
• You struggled to articulate your thoughts or past performance during the interview, making it difficult for the hiring team to gauge
• You didn’t know enough about the company and position.
• There were more qualified candidates.

How you fix it

• Document your work history (roles, responsibilities, projects, accomplishments) and try to memorize the important details that might come up in conversation.
• Practice and master answering behavioural questions. Common questions include:
  
  • Tell me about a time when you had to deal with a difficult coworker.
  • Describe a situation where you had to overcome a significant challenge at work.
  • How have you handled a situation when you had to meet a tight deadline?
• Use the STAR method when answering questions. STAR stands for Situation, Task, Action, and Result. Structure your response by describing the situation you faced, the task you were responsible for, the actions you took, and the results you achieved.
  
• Practice your answers out loud - that’ll help you become more comfortable when speaking about your experiences. I’ve personally practiced in front of a mirror and have asked family members to act as the interviewer. The key is to do what works for you!
  
• Master your tone and body language. Good books like "The Nonverbal Advantage" by Kinsey Goman are helpful.
  

---
If you found this post helpful, I talk about stuff like this weekly in my free newsletter, the Job Seeker's Gazette.

Hello everyone! So excited to be admitted to Berkeley and already paid my deposit. However, on cal central my next step is to create a Calnet ID, which I seem to have trouble finding. it's not listed as one of the tasks that need to be completed so I'm not sure where I should go about finding this option? I'm sure this question has been asked b4, but I can't seem to find a solid answer so I was wondering if you guys could give me a hand here...

i woke up today with nothing to do, and yet a great many things to do, which is the usual state of affairs. i write to-do lists endlessly, with schedules that i dont follow, and tasks that are long over due. what good does “make art” have on a fucking to do list?
i guess it makes me feel like im working towards the future~ the one i dream about when i squat in the shower with my ears plugged so the rain becomes like white noise. even though i write “make art” on the list, my shower dreams usually revolve around white sand beaches with hot chicks and ferraris.
there are to-do lists all over my bedroom walls, but i dont look at them much, and eventually i will have to include “look at the old to-do lists” on the new ones.
i sunbathed in the nude, drinking black coffee and sunning my balls. a man on the internet said it was good to sun your balls. it sounds correct to me. i turned over and spread my cheeks to sun my asshole as well.
i wondered if the neighbor across the street would be able to see my cock. he has put up aluminum sun shades in his windows instead of curtains, like the kind you see in car windshields. he has many trash cans, probably three black, three blue, and three green. he puts all of them out each week, and none of us can figure out how he creates so much trash every week. he has not had a single visitor in the three years since he moved in. i felt that he might enjoy seeing my cock, i hoped it might give him a thrill, because he really seems to need it.
later, i did not feel like cooking, so i decided to drive to get some food, and because it was late, the only things open were fast food and taco trucks. i got dressed nicely and drove to the taco truck for al pastor, and stopped on the way to buy a pint of whiskey, which i drank surreptitously while driving. i thought of jeff daniels in “something wild” drinking scotch in the car in the same manner, whilst melanie griffith drinks boldly.
the taco truck was busy. several couples stood in front of me, but only one was good looking and well dressed. one of the ugly couples bought a homeless man some food.
i made sustained eye contact with the woman and i thought she might find me sexually attractive. as i waited for my food i got a waft of something that smelled exactly like my ex-girlfriend, which was made stranger by the fact that i had dreamt about her the night before.
the hand sanitizer smelled like cheap perfume, and i used lots of it, having seen the homeless man touch all of the accoutrements.

------------------------------------------------------------------------------------ L1 Task Force
Please find the following summary of work completed for Q1. I am in the process of preparing an end of quarter report, and there are some items that will be included in that report that are not listed here which have also been completed. These additional items include components such as security patches, new feature requests that were approved through governance (i.e. minimum initial deposit for proposals to eliminate scam proposals) and the Cosmwasm v1.1.0 upgrade which was originally required to have an investigation conducted, but has now largely been completed.
I will also provide a separate summary of the other items that have been completed, as mentioned above.
Quarter 1
January, 2023
Establish process and product backlog for L1 team. Completed
Establish a “community oversight committee” for this L1 team, with trusted third parties. (PFC, DJTrev, StrathCole) Completed
Assess the possibility of introducing upgrade handlers to utilize software upgrade governance proposals. Completed
Assess the state of our current “version map” and determine how it can be patched to reflect the current state of our system. Completed
Continue working on the “genesis import” problem to maintain a “fallback strategy” if “version map” cannot be patched. Completed
Adjust ante handler to send 50% of “burn tax” to community pool & 50% to treasury burn wallet. Completed
Test/Upgrade “estimate-fee” client logic (LCD) in auth module to ensure “burn tax” is calculated correctly. Completed
Test/Upgrade IBC denom whitelist. Completed
Propose governance for no canonical github repo. Agora has been posted
Test, push, and upgrade testnet with version 1.0.5 Completed
Test, push, and upgrade mainnet with version 1.0.5 Completed
February, 2023
Investigate PebbleDB/BadgerDb for speed improvements to the backend, discontinue support for goleveldb/rocksdb Completed. See GitHub - classic-terra/db-benchmark 2 for benchmarking and performance information.
Transition to iavl fast node via iavl 0.19.4. Deferred
Implement upgrade handlers to utilize software upgrade governance proposals. Completed
Assess the viability of using cosmovisor for future chain upgrades. Completed
Test upgraded chain to Cosmos SDK v0.45.11 with TFL patches to support oracle. Completed
Test upgraded chain to Tendermint v0.34.21 with TFL patches to support oracle. Completed
Work closely with infrastructure* and L2 wallet providers/partners* on the Classic chain to ensure compatibility with Cosmos 45.11 and Tendermint v0.34.21. Completed
Propose governance for Mev-Tendermint. Not required
Test, push, and upgrade testnet with version 2.0.4 (Modified release to v2.0.0 name) Larger testnet validator set required
Test, push, and upgrade mainnet with version 2.0.4 (Modified release to v2.0.0 name) Targeted for 3rd or 4th week of April.
March, 2023
Investigate updating to canonical version of Tendermint v0.37. Completed
Ensure the priority and compatibility with Oracle transactions (tx) compared to other tx’s once we adopt Tendermint v0.37. Completed
Secure and deploy Oracle with sha256 to all validators. Pending governance approval. Agora proposal has been posted.
Fork TFL Interchain wallet, develop potential solutions to the bech32 problem at the wallet level, and present multiple solutions to TFL.* ** No longer required
Impact analysis of upgrade to Cosmwasm v1.0.0 to assess effect on migrating L2 wasm contracts from 0.16.6. Completed
Augment the current WASM virtual machine to fit with Cosmwasm v1.0.0. Completed
Reach out to Assaf from Secret Network to understand dual VM setup. No longer required.
Conclusions of quarter 1. Community assessment of team activities. Governance vote to continue funding team activities. In progress
------------------------------------------------------------------------------------ community response

Propose governance for no canonical github repo. Agora has been posted

What is the reason for this not being posted back in January and was only just posted now?

Investigate PebbleDB/BadgerDb for speed improvements to the backend, discontinue support for goleveldb/rocksdb Completed . See GitHub - classic-terra/db-benchmark 1 for benchmarking and performance information.

I can see that the repo exists, but where is the benchmarking and performance information in this repo?

Transition to iavl fast node via iavl 0.19.4. Deferred

Can you expand on why this was deferred?

Propose governance for Mev-Tendermint. Not required

Can you expand on why this task was no longer required?

Test, push, and upgrade testnet with version 2.0.4 (Modified release to v2.0.0 name) Larger testnet validator set required

Fair enough. I know this is already a task item that is being worked on, and we’ve had discussions about this specific requirement in the past.

Secure and deploy Oracle with sha256 to all validators. Pending governance approval. Agora proposal has been posted.

Can you expand on why this Agora was only posted now?

Fork TFL Interchain wallet, develop potential solutions to the bech32 problem at the wallet level, and present multiple solutions to TFL.* ** No longer required

Can you expand on why this is no longer required?

Reach out to Assaf from Secret Network to understand dual VM setup. No longer required.

Can you expand on why this is no longer required?
------------------------------------------------------------------------------------ L1 Task Force

Propose governance for no canonical github repo. Agora has been posted

What is the reason for this not being posted back in January and was only just posted now?
When reviewing prioritization stack ranked against other items, we decided to schedule for the end of the quarter.

Transition to iavl fast node via iavl 0.19.4. Deferred

Can you expand on why this was deferred?
This item may be reviewed in the future, but the team felt that it was not required at this time. Results in faster production of blocks, and requires further discussion with the community.

Propose governance for Mev-Tendermint. Not required

Can you expand on why this task was no longer required?
This was a decision that the team made that it was better to not proceed with Mev-Tendermint at this time.

First time builder, building from scratch, obviously. Picked some not-so-popular brands for the RAM, SSD, and PSU. Just wondering if I went too far. I am looking at the Microcenter bundles, too, since I live near one, but I am not sure if that will be cheaper or this thing I specced out.
Primary use is general browsing and schoolwork. Gaming on a 1440/60 Dell monitor. Will be playing various Gamepass games like Halo Infinite, Yakuza series, and then Dota2.
Some story driven games and a big backlog of the free Epic games I never got around to playing like GTAV, Requiem. FF7 Intergrade, too.
PCPartPicker Part List

Type	Item	Price
CPU	AMD Ryzen 5 5600 3.5 GHz 6-Core Processor	$139.79 @ B&H
CPU Cooler	Deepcool AK400 ZERO DARK 66.47 CFM CPU Cooler	$39.98 @ Newegg
Motherboard	MSI PRO B550-VC ATX AM4 Motherboard	$129.99 @ Newegg
Memory	*PNY XLR8 32 GB (2 x 16 GB) DDR4-3600 CL18 Memory	$72.99 @ B&H
Storage	TEAMGROUP MP33 2 TB M.2-2280 PCIe 3.0 X4 NVME Solid State Drive	$109.99 @ Newegg
Video Card	*XFX Speedster MERC 310 Black Edition Radeon RX 7900 XT 20 GB Video Card	$829.99 @ B&H
Case	Corsair iCUE 4000X RGB ATX Mid Tower Case	$109.99 @ Newegg
Power Supply	*Enermax Revolution D.F. 750 W 80+ Gold Certified Fully Modular ATX Power Supply	$109.99 @ Newegg
	Prices include shipping, taxes, rebates, and discounts
	Total (before mail-in rebates)	$1572.71
	Mail-in rebates	-$30.00
	Total	$1542.71
	*Lowest price parts chosen from parametric criteria
	Generated by PCPartPicker 2023-04-01 03:50 EDT-0400

💬 Tell them about #BabyDoge! It's time to shill Exchanges we are not listed on!
Binance:
https://twitter.com/binance/status/1641976185298079744?s=20
Kucoin:
https://twitter.com/kucoincom/status/1641953882124460032?s=20
WazirX:
https://twitter.com/WazirXIndia/status/1642021502479396865?s=20
Phemex:
https://twitter.com/Phemex_official/status/1641926597564399616?s=20
Hotcoin:
https://twitter.com/HotcoinGlobal/status/1641989160486707205?s=20
BTCEX:
https://twitter.com/BTCEX_exchange/status/1642015821907230720?s=20
Toobit:
https://twitter.com/Toobit_official/status/1642016691151581184?s=20
​
(NEW)⌨️ Interact with the latest tweet (like, retweet, comment):
https://twitter.com/BabyDogeCoin/status/1641786070068256768?s=20
(NEW)⌨️Interact with the latest Instagram post (like, comment):
https://www.instagram.com/p/Cqc2vSnO4qX/?utm_source=ig_web_copy_link
(NEW)⌨️Interact with the latest Facebook post (like, share, comment):
https://www.facebook.com/photo?fbid=546090291001135&set=a.507289728214525
⌨️ Interact with the latest CMC post (like, repost, comment):
https://coinmarketcap.com/community/post/323509242
​
​
📅 DAILY TASKS: It will only take a few seconds. You can vote every 24h.
No login needed.

1. Hit up CMC and hit the GOOD Button 👍

https://coinmarketcap.com/currencies/baby-doge-coin/

1. Hit up Coingecko and hit the GOOD Button 😁

https://www.coingecko.com/en/coins/baby-doge-coin

1. Hit up cryptocom and hit the GOOD Button 👍

https://crypto.com/price/baby-doge-coin

1. Vote for BabyDoge on CryptEye 🔥

https://www.crypteye.io/coin/baby-doge-coin
​
​
📈 Help us Get Trending:
Simply click the link, let the website load and close the page! No other action needed.
1.https://www.google.com/search?q=babydoge
2.https://www.google.com/search?q=baby%20doge%20coin
3.https://www.google.com/search?q=babydoge%20binance
4.https://www.google.com/search?q=babydoge%20nft
5.https://www.google.com/search?q=babydogeswap
6.https://www.youtube.com/results?search_query=babydoge
​
Simply click the link, type babydoge in the search bar, click on baby doge coin, let the website load and close the page. Done! As simple as that.

1. Go to https://coinmarketcap.com

SEARCH for 'babydoge'.

1. Go to https://www.coingecko.com

SEARCH for 'babydoge'.

1. Go to https://www.certik.org

SEARCH for 'babydoge'.

1. Go to https://cryptorank.io/

SEARCH for 'babydoge'.

1. Go to https://markets.coin98.com

SEARCH for 'babydoge'.

1. Go to https://lunarcrush.com/

SEARCH for babydoge.
​
Have a nice day guys!

What will you be doing with this PC? Be as specific as possible, and include specific games or programs you will be using.

Gaming, mostly Rust, but also typical watching YouTube/Twitch and Discord all open at once.

What is your maximum budget before rebates/shipping/taxes?

$1500.

When do you plan on building/buying the PC? Note: beyond a week or two from today means any build you receive will be out of date when you want to buy.

ASAP when the 7800X3D drops/arrives.

What, exactly, do you need included in the budget? (ToweOS/monitokeyboard/mouse/etc)

CPU/MOBO/RAM/PSU.

Which country (and state/province) will you be purchasing the parts in? If you're in US, do you have access to a Microcenter location?

US, Minnesota, yes I have access to a Microcenter.

If reusing any parts (including monitor(s)/keyboard/mouse/etc), what parts will you be reusing? Brands and models are appreciated.

RTX 2070S, Storage Devices, Case (4000D Airflow), and all peripherals are being reused.

Will you be overclocking? If yes, are you interested in overclocking right away, or down the line? CPU and/or GPU?

Slight GPU OC, and Memory Tuning.

Are there any specific features or items you want/need in the build? (ex: SSD, large amount of storage or a RAID setup, CUDA or OpenCL support, etc)

N/A.

What type of network connectivity do you need? (Wired and/or WiFi) If WiFi is needed and you would like to find the fastest match for your wireless router, please list any specifics.

Wired Only.

Do you have any specific case preferences (Size like ITX/microATX/mid-towefull-tower, styles, colors, window or not, LED lighting, etc), or a particular color theme preference for the components?

Already have 4000D Airflow Black. Looking for all Black, Black/White, and no RGB for components

Do you need a copy of Windows included in the budget? If you do need one included, do you have a preference?

No.

https://pcpartpicker.com/list/vsPdZw
I have a few questions about this build:
1) can I fit any large GPU (like those big ones with 3 fans etc.) in this case?
2) What PSU should I go for?
Many thanks!!

People or articles that promote Dumbphones over smartphones are making the argument that dumbphones are simplyfing your life. This is not true. It does make it more complicated. You need to print out maps when you want to go somewhere. You can't just chose the song you like on your phone and listen to it, you need to go to a store and order the CD. You need to buy train tickets on a ticket machine instead of just getting it with a few clicks on your phone. You can't just simply get the information you want anytime, you have to wait until you get home. The list goes on and on. Smartphones are so addicting because they simplify many tasks in life.

We All Bought Furniture's From Scrooge McDucks Shop And Use Them As Decoration around the biomes but it's get "kinda boring" that ur just looking at it, but not Using them! and i wish that it was functionable so make it more useable without it just being there being pretty just to look at it.
Here Are 6 Things I Want In Disney Dreamlight Valley that The Furniture's To Be Functionable, i wish that the disney dreamlight Valley Team Well See This And Hope It Will Get Added In The Future Updates if possible if it's up to them to make it happen or not that i want it to be use.
​

1. I Wish That The Bath/Tub and Would Be Functionable Would Make Our Characters Be Clean After A Hard Work From The Outside Just To Relax In The bath/Tub And It Well Help Our Energy Fill All The Way Up To The Yellow bar so it can be cool to see it work so anyone from the village can use it if they want to get clean or just to relax in it or have fun in it.
2. i Wish That The Sink Would Be Functionable So Our Characters Or The Villager's Can Wash Their Hands In The Sinks whatever task they do so there hands can be clean and also it can help with the energy fill all up to the full blue bar.
3. I Would Like To See The Swimming Pool And The watering hole Be Functionable So Our Characters Or Villagers Can Use It To Have Like Fun In It To Relax Or Swim and maybe both of them can help with the energy bar that be kinda nice
4. book case would be cool to see it functionable so our character and villager's can sit down and read the book.
5. i like to see the Tv Or The Computer would be functionable it can work to look up weather channel to see if it going to rain or be sunny or foggy or whatever and have cooking channel to get recipes that u can unlock and or just watch tv or play games on the computer.
6. And Wish that ur character can relax in the bed or sleep in the bed or talk on the bed with villager's or watch tv from the bed or read a book on or in the bed would be nice and cool addition to make it functionable.

there are the things i wish to see be functionable and would be nice to have it so our characters or villager's can use it more i know it probably would take lot of animations to make it work but be nice to have more things to have fun to do in Dreamlight valley.
now on for the bugs fixes i wish the disney dream light valley team can fix that i'm having issue with

1. Some Reason Prince Eric won't follow u anymore everytime u ask him he said sure but doesn't follow u so please fix this disney dreamlight valley team
2. 2. Stitch Tv is invisible it won't show up at all i have it in my furniture's inventory but i can't use it for Decoration so i don't know why it doing that but it needs to be fix please
3. 3. When u order things to scrooge there are items u can't get it since it doesn't have the names on them like what the character use during there side quest it show up in scrooge shop but u can't buy it at all and it's very strange because there really good items want to use it for Decoration but u can't :{ ?
4. Slow Loading Screen issue when in loading screen keeps freezing and moving and freezing and moving and the music keeps playing overlapping each other like 3 or 4 times or more until u can get in the game? and this is happening on Ps4
5. Everytime u play the game the game keep have error code every time and u had to close it down and restart to play it so very annoying?. This Is Happening On Ps4
6. And one more thing when u receiving items or critters sometimes the game won't click when u accept them u have to close the game and restart it but even tho u get the critters or items u have to restart to make sure u got them, so very annoying can u please fix this please i would be so greatful? This Is Happening On Ps4
   
7. so anyway that all the bugs and glitches and i have problem with And things i want to be functionable on the furniture's list and TBH this is my first time post on this reddit but thanks for hearing me out and God bless u all Disney Dreamlight Valley Fans and have great day love ya'll.
   

I have a container with the same to-do list on two different pages. Whenever I need to check something or add a new task I need to do it twice on both pages. Is there anyway I can do it only on one of the page and it sync to the same container on another page?

So had this dream last night/this morning and haven't had anything like it before:
In Turkey with a couple of friends I am not too close with anymore.
We're on a high rise and could see the army were out killing people, but with some order. They were tasked to do this based on a list they had. Almost like Thanks killing half the population. We were safe where we were so we're recording on our phones. Then found ourselves on a hot air balloon just seeing mass murder being committed, the army using these were mine-like flamethrower things that were disposable. Soon after we found ourselves falling from the balloon, into a field close to some of the army. Myself and both friends were instantly scared, so naturally we ran for our lives, with army chasing us. We couldn't get far in the long grass and the army general said "we promise we won't kill you". We surrendered. He approached us. He was middle aged, stubbly, bald and had several gold chains on. He told us to get on our knees, then he asked "what is your date of birth?", I told him and he said "it's funny we always know our date of birth but we don't think about the other side" (almost like a line in a movie), it was inevitable I was about to die. I closed my eyes, prayed to Krishna and then my dream ended.
Any thoughts?

Hi everyone! This is the Accountability Thread where people can list what they need or want to accomplish today and have everyone else help keep you accountable to do them. So, in general a post will look like this:
Things I have to get done today:
1: Post Accountability Thread
If I had more to do that I had not completed I would list them and update this when these things were complete.
Also, if I saw someone doing something that I happen to be well-educated or have some sort of expertise in I can offer support or help on the topic/task.
The thread is a versatile one, use it in a way that helps you and others stay on task!
Happy studying!

This is my build:
PCPartPicker Part List

Type	Item	Price
CPU	Intel Core i7-13700K 3.4 GHz 16-Core Processor	$399.99 @ Newegg
CPU Cooler	ID-COOLING FROSTFLOW X 74.5 CFM Liquid CPU Cooler	-
Motherboard	Gigabyte Z790 UD AC ATX LGA1700 Motherboard	$194.99 @ Amazon
Memory	Corsair Vengeance 64 GB (2 x 32 GB) DDR5-6000 CL40 Memory	$284.99 @ Corsair
Storage	Kingston NV2 2 TB M.2-2280 PCIe 4.0 X4 NVME Solid State Drive	$99.99 @ Amazon
Video Card	NVIDIA Founders Edition GeForce RTX 4080 16 GB Video Card	$1378.99 @ Amazon
Case	NZXT H7 Flow ATX Mid Tower Case	$129.99 @ Best Buy
Power Supply	NZXT C1000 (2022) 1000 W 80+ Gold Certified Fully Modular ATX Power Supply	$179.99 @ Newegg Sellers
Operating System	Microsoft Windows 11 Home OEM - DVD 64-bit	$117.98 @ Other World Computing
Monitor	Gigabyte ‎M32UC 31.5" 3840 x 2160 160 Hz Curved Monitor	$599.99 @ Amazon
	Prices include shipping, taxes, rebates, and discounts
	Total	$3386.90
	Generated by PCPartPicker 2023-04-01 02:43 EDT-0400

I'm following the LTT build guide and booted to bios before putting everything in my case. Everything was going well until my CPU temp started climbing... And didn't stop. It hit 100°C and then I turned the PSU off to avoid damaging anything.
I hooked up my cooler to my CPU and tightened the connections quite a bit. I figure this must be a thermal paste issue? I'm using the paste that came with my AIO, Frost X25. Another significant detail is that the AIO radiator and fans are just sitting on the table, so they aren't doing any cooling. I assume once they're in the case they'll help a bit with cooling.
When I took my AIO off and examined the paste, it looked like this: https://imgur.com/gallery/9QNzzka
Does this seem like enough paste? Too much paste? If it's not the paste, what are the other common causes of high CPU temps?
I should have taken a picture of the bios, but one significant thing I remember was the CPU voltage was 1.1V. Should I look into under volting?
Thanks in advance for your help!

Freecash has launched a new $50 giveaway! You can participate here.
Introduction
Having recently gotten into beermoney websites myself I quickly ran into a problem - being located in Eastern Europe it is difficult to find something that actually works. So, I've spent some time and gathered around a fair amount of websites that I personally tested to see if they worked for real or not. These were tried out in Estonia but should work worldwide. It is highly recommended to combine various websites in order to maximize earnings.
Please don't hesitate to share any beermoney websites that you know as well. Be aware that most of these websites require verified PayPal in order to process withdrawals, so make sure you have that sorted out. This list is updated whenever a new method is found!
Sign-up offers can be found in a separate thread.
We have launched a dedicated beermoney blog, BeermoneyGuides! It will feature more in-depth guides and reviews for beermoney methods listed here.
Mobile applications
We'll start with some of the mobile applications that I have found. Note that these are all for Android so you will have to double-check whether an iOS version is available.

Application	Description
AttaPoll	Surveys. Withdrawals starting at 3€. One of the best paying mobile applications! Use code gwbdj if prompted for a one-time bonus
Freecash	GPT website that has a mobile application available.
Jumptask	Another GPT platform that also has a mobile app.
methinks	Paid interviews and surveys.
Quicrypto	Crypto surveys, tasks and offers.
Paidwork	Mobile GPT app (games, ads, surveys, offers).
mCrypto	Play mobile games for crypto.
Sweatcoin	App that pays you for how much you walk each day (counts steps).
RepaysMe	Get paid for sending out SMS. (Attention: This sends out SMS, so be aware).
SEAgent	Receive money for SMS, enter code csjs3aej when registering for a bonus.
MoneySMS	Get paid for receiving SMS! Enter code V1V439JO when registering for a one-time bonus.
McMoney	Same as MoneySMS, get paid for receiving SMS. Enter code MYYQXC03 for a bonus! (can run both at the same time)
COIN	Receive rewards for geomining.
ClipClaps	Get paid for watching various videos. After registering you can use code 0367175209 for a one time gift!
BigCash	Mobile games and surveys. After installing you can enter code c3b20wia to receive extra credits.
SurveyPirate	Application for surveys and offers, for a bonus you can enter code 7134JPJD after registering.
Litecoin Giveaway	Litecoin app that lets you earn LTC.
Free Bitcoin Cash	Similar to the app above (same dev), just for Bitcoin Cash (BCH) instead.
Earn Litecoin	Application for earning Litecoin, just made by another developer.
Earn Bitcoin Cash	Application for earning BCH, same developer as Earn Litecoin.
CashMagnet	Mobile farming, passive.
Premise	Short surveys and tasks that require you to take pictures of places around your town. You can withdraw starting at 4€.
Cointiply	Bitcoin GPT website, on a phone you can earn passively by using playtime offerwall. Passive earning on mobile!
Mode Earn	Pays you to listen to music and you can also complete various tasks.
appKarma	Various paid offers (such as games).
cashKarma	Surveys and other additional offers.
CryptoTab	Browser built-in mining.

Passive methods
These are passive ways to earn money! They just require initial setup, probably the most hassle-free way to earn additional income.

Passive applications	Description
Peer2Profit	Passive income website for selling unused internet traffic. Highest paying $/GB rate!
Honeygain	Additional similar method for sharing for your extra bandwidth.
Jumptask	You can withdraw your Honeygain credits via JumpTask and also stake them, has various offers and surveys as well that you can complete.
Hideout	Get paid for watching ads on videos. Combine with Lootup to get the best exchange rate.
PacketStream	Bandwidth sharing.
Slice	Browser extension where you get paid for viewing ads. (NEW!)
Pawns.app	Get paid for sharing internet data (also has surveys).
Kryptex	Cryptocurrency mining.
EarnApp	Another way to earn money for unused internet bandwidth.
unMineable	Cryptocurrency mining.
eBesucher	Passive earning method for essentially giving traffic to different websites (surfbar).
adBTC	Has an autosurf option like eBesucher, just pays in BTC. Can also watch various ads.
Proxyrack	Sell unused internet data.
LoadTeam	Get paid for sharing your CPU power.
Repocket	Sell unused internet data.
ProHashing	Cryptocurrency mining.
Traffmonetizer	Sell unused internet traffic.
SpideNetwork	Sell internet bandwidth.
Income Spider	Sell unused internet data.
Bitping	Sell internet data.

Get-Paid-To (GPT)
As the title suggests, "Get-Paid-To" websites pay you to do certain tasks. Now there might not be too many surveys available that work, but offers can be well worth doing in my opinion. Take some time to browse around to see what is available (for example, mobile game offers). Once you have found something I recommend to start comparing rates that different GPT websites are offering (for example, game X with offerwall Y is available both on Freecash and Swagbucks, but Freecash has a higher payout for completing the same task).
Generally the games offered are very grindy but not impossible to complete. Patience is key, make sure to do your research about offered games to see which ones are the easiest.

Website	Description
Freecash	Includes various games, offers, tasks and surveys. Probably the best paying GPT site at the current moment!
ySense	Games, offers, tasks, surveys. Very good global GPT option!
Lootup	Games, offers, tasks, surveys. Use in combination with Hideout for passive earning!
Swagbucks	Games, offers, tasks, surveys. Has an addon you can install to get notified of any new offers instantly.
SimpleBits	Crypto PTC, faucet, various offers.
Mintalise	Get paid for completing offers and surveys.
FeaturePoints	Various GPT surveys, offers, tasks.
Grindbux	GPT offers and surveys.
GaintPlay	Various offers, task, games.
Chequity	Faucet, games, surveys, offers.
BeerSurveys	Made by creators of the biggest beermoney forum, has sometimes exclusive offers. Features surveys, downloading apps, watching videos.
Rewardxp	You can also use hideout here if you prefer, has games, offers, surveys and more.
KeepRewarding	Various offers, watching videos, PTC.
CoinsBaron	Crypto surveys and GPT.
RewardingWays	Various offers and surveys.
SuperPay	Surveys & offers.
InstaGC	Tasks, offers, surveys, videos.
GrabPoints	Tasks, surveys, offers.
Freeward	Offers, surveys, tasks.
timebucks	Different tasks, offers, games, surveys.
Cointiply	Bitcoin GPT website, has a passive playtime offerwall.
gain.gg	Games, offers, tasks, surveys.
GG2U	Games, offers, tasks, surveys.
AutoFaucet	Check in often to do rolls! Has various offers, games tasks, surveys.
GamerMine	Games, offers, tasks, surveys.
PrizeRebel	Games, offers, tasks, surveys.
FireFaucet	Games, offers, tasks, surveys.

Tasks/micro jobs
These sites offer micro jobs, which are basically small tasks that you can perform for payment. It is recommended to use multiple micro jobs sites at once as each site has unique tasks.

Website	Description
YandexToloka	Lots of smaller tasks that you can complete for money. Best paying tasks!
Nomadtask	Complete tasks for money.
Aviso	Get paid for tasks such as watching videos. (NEW!)
TaskVerse	Various paid tasks.
Remotasks	Get paid for completing various tasks (you can earn a bonus 10$ if you complete a task within 2 weeks of registering).
SproutGigs	Small tasks/micro jobs (previously Picoworkers)
clickworker	Lots of various projects and tasks.
Freecash	Paid GPT tasks.
Maven	Get paid by sharing expertise on various topics.
Fiverr	Freelancing opportunities.
Zeerk	Freelancing opportunities.
SeoSprint	Many tasks that you can complete for payment. (NB! It's in Russian but you can use Google Translate)
OneForma	Data collection projects and jobs such as transcription etc..
GoTranscribe	Transcription jobs.

Other
These sites will pay you for various actions, such as performing internet searches, watching videos and more.

Website	Description
SerpClix	Pays you to do simple google/bing searches. (Semi-passive!)
SerpBot	Similar to SerpClix, get paid for visiting websites.
Gamehag	Complete video game quests for money.
Apperwall	Write short reviews about various products.
Bonusbank	Matched betting.
doodstream	Get paid for sharing videos.
Gener8	View ads when surfing.
imdbux	PTC/get paid for viewing ads.
Bananatic	Kind of like Gamehag, various video game quests that you can complete.
photomath	Get paid for doing math.
2captcha	Solve captchas.
Submithub	Make money with your spotify playlists/social media.
BUFF	Application that pays you to play video games.
Honeygain	Completely passive earning for your extra bandwidth, also available for desktop devices.
GameTester	Lets you playtest video games for rewards.
ebesucher	Another passive earning method for essentially giving traffic to different websites (surfbar).
Andromo	Build applications that you can later monetize.
COIN	Receive rewards for geomining and more!
FruitLab	Get paid for watching gameclips.
Honey	Save money and get cashback on your online purchases (browser extension).
Airtm	Convert giftcards and more into real money.

Crypto
Websites that focus mostly on cryptocurrencies.

Website	Description
Cointiply	Bitcoin GPT website. Best website to earn crypto!
RollerCoin	Virtual bitcoin mining game.
FreeBitco.in	Probably most well known bitcoin faucet, check-in once an hour to do rolls.
bc.game	Crypto betting/games.
Litepick	Faucet for earning Litecoin. (NEW!)
Freecash	GPT website where you can withdraw using multiple crypto options.
SweatFaucet	Faucet for Sweatcoin.
CoinPayU	Get paid for viewing ads.
CoinsBaron	Crypto surveys and GPT.
unMineable	Crypto mining.
EarnCrypto	Crypto surveys and offers.
BetFury	Crypto games/betting.
adBTC	Get paid in BTC for watching ads/autosurfing.
Idle-Empire	Crypto GPT website.
Crypto4Winners	Crypto investment fund.
PipeFlare	Earn crypto by playing.
Womplay	Play games for crypto.
Permission.io	Get paid for watching videos.
Publish0x	Earn crypto by blogging.
Litecoin Giveaway	Litecoin app that lets you earn LTC.
Free Bitcoin Cash	Similar to app above (same dev), just for Bitcoin Cash (BCH) instead.
Earn Litecoin	Application for earning Litecoin, just made by another developer.
Earn Bitcoin Cash	Application for earning BCH, same developer as Earn Litecoin.
CryptoTab	Browser built-in mining.

Cryptocurrency exchanges
Recommended cryptocurrency exchanges to sell your earned crypto for fiat.

Website	Description
Kraken	Cryptocurrency exchange.
Binance	Cryptocurrency exchange.
Crypto.com	Cryptocurrency exchange.

Studies, surveys
Some websites that offer studies/surveys.

Website	Description
PaidViewpoint	Surveys. Make sure to visit at least once a day to keep consistently building up the trait score. Best surveys! High potential earnings once the trait score is built up.
surveyeah	Surveys. Has an Anrdoid application available called "OpinionAPP".
Surveytime	Surveys. No minimum withdrawal. Instant payments.
Pawns.app	Internet sharing app that has surveys available on mobile.
HeyPiggy	Various surveys.
Respondent	Research studies.
SurveySavvy	Surveys.
Freecash	GPT website with a separate survey section, many different options are available (CPX research, Bitlabs and more)
Prolific	Various studies.
OpinionPioneer	Surveys.
Testable Minds	Studies. Turn on browser notifications to be notified whenever a study is available as places are reserved extremely quickly.
PingPong	Studies. Don't forget to enable e-mail notifications in the settings menu.
MarketAgent	Surveys. Make sure to fill out the profile extension section!
MOBROG	Surveys. Also available on iOS/Android.
Spidermetrix	Surveys.

Usertesting
Websites that offer software/website/other testing

Website	Description
test.io	Website and software testing.
UserAdvocate	UX testing.
TestingTime	UX testing.
TestBirds	Website testing.
UserCrowd	UX testing (short tests).
BetaTesting	Software testing.
Testlio	Software testing.
Conversioncrimes	UX testing.
UserFeel	UX testing.
Validately	UX testing.

Websites to avoid!
❌PollPay - company refuses to send out payment and their support has not been replying back for a while now.