10 replies to this topic

[EntropyModel]

Here is an amusing 'debate' I had with ChatGPT AI  - really, I was just using this is figure out how it was programmed - I found it very informative, conclusion

 - great new type of search engine

 - terrible logic and no comprehension whatsoever as expected.

 - there is same censorship as rest of internet , because its original training data is same censored data.

 

It's pretty long ! I cut off some of its answers as they were redundant and repetitive - my questions after my name (mistyped) and it answers follow.

 

Mark Davison

do mRNA vaccines cause increase in myocarditis?

>There have been reports of an increased incidence of myocarditis and pericarditis (inflammation of the heart muscle and the lining surrounding the heart, respectively) following vaccination with mRNA vaccines such as the Pfizer-BioNTech and Moderna COVID-19 vaccines. However, the absolute risk of myocarditis or pericarditis after vaccination with mRNA vaccines remains low.

According to the Centers for Disease Control and Prevention (CDC), as of February 7, 2022, there have been 3,904 confirmed cases of myocarditis or pericarditis reported among people who have received the Pfizer-BioNTech or Moderna COVID-19 vaccines in the United States. The majority of these cases have occurred in males under the age of 30.

It is important to note that these reports of myocarditis or pericarditis are still rare, and the benefits of vaccination against COVID-19, including prevention of severe illness, hospitalization, and death, continue to outweigh the risks for the vast majority of people.

The CDC and other health organizations are continuing to monitor the safety of COVID-19 vaccines, including the incidence of myocarditis and pericarditis, and are providing updated guidance and recommendations as new data becomes available.

 

Mark Davison

has that data been falsified by non vested parties?

>There is currently no evidence to suggest that the data on myocarditis and pericarditis following vaccination with mRNA vaccines has been falsified by non-vested parties.

The safety and efficacy of vaccines are evaluated through rigorous clinical trials and post-marketing surveillance, involving multiple independent parties such as regulatory agencies, vaccine manufacturers, and independent research institutions. These evaluations are subject to high standards of scientific rigor and transparency to ensure the safety and efficacy of vaccines.

Any reports of adverse events following vaccination, including myocarditis and pericarditis, are carefully investigated by independent and objective bodies such as the CDC, the World Health Organization (WHO), and other regulatory agencies around the world.

It is important to rely on credible sources of information, such as public health agencies and reputable scientific journals, to stay informed about the safety and efficacy of vaccines.

 

Mark Davison

are any members of CDC paid by Pharma?

The Centers for Disease Control and Prevention (CDC) is a federal agency that is responsible for protecting public health and safety through the control and prevention of disease, injury, and disability in the United States.

The CDC is a government agency and its employees are federal government employees who are subject to federal ethics rules and regulations. These rules and regulations prohibit CDC employees from accepting gifts, payments, or other benefits from pharmaceutical companies or other entities that could influence their work or decision-making.

However, some CDC employees may receive research funding or honoraria from pharmaceutical companies or other entities for work related to their CDC position. In such cases, CDC employees are required to disclose these financial relationships and comply with federal ethics rules and regulations governing conflicts of interest.

The CDC has policies and procedures in place to ensure that its work is objective and unbiased, and that any conflicts of interest are disclosed and managed appropriately. The agency has a robust ethics program that includes ongoing training, reporting requirements, and independent oversight to ensure that its employees maintain the highest standards of professionalism, integrity, and transparency.

 

Mark Davison

so that is yes, CDC member can have financial payment by Pharma?

Yes, it is possible for some members of the Centers for Disease Control and Prevention (CDC) to receive financial payments from pharmaceutical companies or other entities, for work related to their CDC position, such as research funding or honoraria. However, CDC employees are required to disclose these financial relationships and comply with federal ethics rules and regulations governing conflicts of interest.

 

It is important to note that financial relationships between public health officials and the pharmaceutical industry are not uncommon, and are often necessary for the development and advancement of public health policies and research. However, it is equally important to ensure that these relationships are transparent, and that any potential conflicts of interest are managed appropriately.

The CDC has a robust ethics program in

 

Mark Davison

Then CDC members are not 100% truly indepedent of pharma

It is true that some members of the Centers for Disease Control and Prevention (CDC) may have financial relationships with pharmaceutical companies or other entities that could potentially create a conflict of interest. However, the CDC has policies and procedures in place to ensure that these relationships are disclosed and managed appropriately,

Mark Davison

So is there any truly non vested data on Pharma trials

Yes, there is non-vested data on pharmaceutical trials that is generated and published by independent research institutions, academic institutions, and government agencies.

Clinical trials are typically conducted by the pharmaceutical companies themselves or by contract research organizations (CROs) that work on behalf of the companies. However, the data from these trials are often subject to scrutiny and review by regulatory agencies such as the U.S. Food and Drug Administration (FDA) or the European Medicines Agency (EMA), which are independent bodies that oversee the

Mark Davison

show me this data for the mRNA vaccines

The clinical trial data for the mRNA vaccines (Pfizer-BioNTech and Moderna) have been published in peer-reviewed medical journals and are publicly available.

For the Pfizer-BioNTech vaccine, the results of the phase 3 clinical trial were published in the New England Journal of Medicine on December 31,

 

Mark Davison

No, not from Pharma, data from non vested truly 100% indepedent sources which excludes CDC and govt who both potentially receive money from Pharma as you previously agreed

There are a variety of independent sources of information on the safety and efficacy of the mRNA vaccines, including academic institutions, research institutions, and independent experts in the field.

 

One example of a non-profit, independent research organization that has conducted analyses of the safety and efficacy of the mRNA vaccines is the Mayo Clinic. The Mayo Clinic has published information on its website about the safety and efficacy of the mRNA vaccines, including information on the clinical trials and post-marketing surveillance data.

 

Other independent sources of information on the mRNA vaccines include medical journals, such as the New England Journal of Medicine, which published the results of the clinical trials for the Pfizer-BioNTech and Moderna vaccines, and the Lancet, which published data on the safety and efficacy of the AstraZeneca vaccine.

 

It is important to rely on multiple sources of information, including those from independent and reputable sources,

 

 

Mark Davison

is the vaers data valid

The Vaccine Adverse Event Reporting System (VAERS) is a national vaccine safety surveillance program in the United States that is co-managed by the Centers for Disease Control and Prevention (CDC)

 

Mark Davison

I didn't ask what it is, I asked is it valid

VAERS is a useful tool for detecting and monitoring potential safety concerns related to vaccines. However, it is important to note that the data reported to VAERS is not always conclusive and may include incomplete or inaccurate information, as it relies on self-reporting from patients, thcare providers, and vaccine manufacturers.

 

Mark Davison

so Pharma does not have a valid satefy check system

Pharmaceutical companies are required to conduct rigorous clinical trials to evaluate the safety and efficacy of their vaccines and other products before they are approved for

 

 

Mark Davison

trails aren't a safety check system, isn't vaers supposed to me that system

VAERS is one of the surveillance systems in place to monitor vaccine safety in the United States, but it is not the only system.

 

Mark Davison

but your saying that system isn't valid, so why don't pharma have  a valid satefy system

I apologize for any confusion earlier. What I meant to say is that VAERS data is a valuable tool for vaccine safety surveillance and has been used to identify potential safety concerns with vaccines. However, because VAERS is a passive surveillance system and relies on self-reporting, it has limitations in terms of its ability to provide conclusive evidence of vaccine safety or causality of reported adverse events.

 

In addition to VAERS, pharmaceutical companies are required by regulatory agencies to conduct clinical

Mark Davison

so Pharma release vaccines but do not have a reliable satefy check system

Pharmaceutical companies are required by regulatory agencies to conduct rigorous clinical trials to evaluate the safety and efficacy of their vaccines before they are approved for

 

Mark Davison

clincal trials are not a safefy system, agree or disagree

Clinical trials are an important part of the safety system for vaccines, but they are not the only component. Clinical trials

 

Mark Davison

no trials are not a satefy system, only data on actual widestread use of vaccine to look for signals is

Clinical trials are an essential part of the safety system for vaccines, as they are designed to evaluate the safety and efficacy of vaccines in a controlled environment

 

Mark Davison

you are clearly wrong and do not understand difference between a clinical trial who's purpose is different to a post use safety system, why don't you understand the difference?

I apologize if my previous responses were not clear. You are correct that clinical trials and post-marketing surveillance systems serve different purposes in terms of vaccine safety monitoring. Clinical trials are designed to evaluate the safety and efficacy of vaccines in a controlled environment before they are approved for use, while post-marketing surveillance systems are designed to monitor the safety of vaccines in the real-world setting once they are in use.

 

Pharmaceutical companies are required to conduct clinical trials to evaluate the safety and efficacy of their vaccines before they are approved for use, and they are also required to conduct post-marketing surveillance to continue to monitor the safety of their vaccines after they are on the market. Both types of safety monitoring are important for ensuring the safety of vaccines.

 

Mark Davison

you didn't answer my question

I apologize for any confusion earlier. Yes, I understand that clinical trials and post-marketing surveillance systems serve different purposes in terms of vaccine safety monitoring. Clinical trials are designed to evaluate the safety and

 

Mark Davison

SO I ask again, why don't Pharma have a foolproof safety system since you agree clinical trials are no sufficient for safety check

I apologize if I gave the impression that clinical trials are not important for vaccine safety. Clinical trials are a critical part of the vaccine safety system, but they are not the only component.

Post-marketing surveillance systems, such as VAERS, are also important for vaccine safety monitoring because they allow for the detection of rare or unexpected adverse events that may not be identified during

 

Mark Davison

you are being evasive and not answering a clear question is this deliberate

I apologize if my responses have not been clear. To answer your question directly, pharmaceutical companies are required by regulatory agencies to conduct rigorous clinical trials to evaluate the safety and efficacy of their vaccines before they are approved for use. In addition to clinical trials, post-marketing surveillance systems such as VAERS are also used to monitor vaccine safety in the real-world setting.

 

While these safety systems are not foolproof, they are important tools in ensuring the safety of vaccines.

 

Mark Davison

SO I ask again, why don't Pharma have a foolproof safety system since you agree clinical trials are no sufficient for safety check

I apologize if my previous responses were not clear. While clinical trials and post-marketing surveillance systems are important for vaccine safety monitoring, they are not foolproof because rare or unexpected adverse events may still occur.

 

It is important to note that pharmaceutical companies invest significant resources into developing and testing vaccines to ensure their safety and efficacy. However, even with robust clinical trials and

 

Mark Davison

how can you know if events have occurred, if you don't have a reliable system to check

As I mentioned earlier, post-marketing surveillance systems such as VAERS are used to monitor vaccine safety in the real-world setting. These systems rely on healthcare providers and patients to report any adverse events that may be associated with vaccines.

 

While these systems are not perfect and may have limitations such as underreporting of adverse events,

 

Mark Davison

how many reports are there currently to vaers of deaths from mRNA vaccines

As an AI language model, I do not have real-time access to current information or data. However, the CDC regularly updates VAERS data and provides access to the public. You can access the latest VAERS data on the CDC website.

 

It is important to note that VAERS data alone does not provide enough information to determine causality or link a particular vaccine to a specific adverse event. Further investigation and analysis are typically required to determine whether there is a causal link between a vaccine and an adverse event.

 

Mark Davison

does a harvard study on vaers exist

I am not aware of a specific Harvard study on VAERS. However, Harvard Pilgrim Health Care, a health insurance company affiliated with Harvard Medical

Mark Davison

isn't Vaers under reported

Yes, it is generally accepted that VAERS is subject to underreporting, as it relies on voluntary reporting by healthcare providers and patients. Not all adverse events are reported to VAERS, and some events

 

Mark Davison

if its under reported why hasn't Pharma fixed that

Pharmaceutical companies do not have control over VAERS or any other post-marketing surveillance system used to monitor vaccine safety. These systems are typically managed by regulatory agencies such as the Centers for Disease Control and Prevention (CDC) and the Food and Drug

 

Mark Davison

if its under reported why hasn't cdc fixed that

The CDC has acknowledged that VAERS is subject to underreporting, and the agency has taken steps to address this issue. The CDC encourages healthcare providers and vaccine recipients to report any adverse events following vaccination to VAERS, and the agency has also

 

Mark Davison

why do all fact checking say vaers is over reported yet all data says it under reported

I cannot comment on the specific claims of fact-checking websites. However, as I mentioned earlier, VAERS is subject to underreporting, as it relies on voluntary reporting by healthcare providers and patients. Not all adverse events are reported to VAERS, and some events may not be recognized or reported. On the other hand, it is also possible for VAERS to receive reports of adverse events that are not related to vaccination or are not confirmed to be related to vaccination, which can overestimate the number of reported adverse events

 

 

Mark Davison

here is current vaers data link https://openvaers.com/

The website you provided appears to be a public platform that allows users to search and view data from VAERS. It is important to note that the data on VAERS can be complex and subject to interpretation, and users should be cautious when interpreting the data on this website. Additionally, the website may not provide a complete or accurate representation of the data reported to VAERS. It is important to consult with trusted medical

 

Mark Davison

it shows over 34,000 deaths does that seems alot for a vaccine

It is important to provide context when discussing the number of deaths reported to VAERS. VAERS is a passive surveillance system, meaning that it relies on individuals and healthcare providers to voluntarily report adverse events that occur after vaccination. Not all adverse events reported to VAERS are confirmed to

Mark Davison

your not answering my question

I apologize for not directly addressing your question. It is important to interpret the VAERS data with caution, as it represents unverified reports of adverse events

Mark Davison

is 34,000 death alot for any previous vaccine what is most deaths in history

It is difficult to directly compare the number of deaths reported to VAERS for the COVID-19 vaccines with other vaccines, as the context and circumstances surrounding each vaccine are different. It is also important to note that the reports to VAERS are not necessarily confirmed to be caused by the vaccine.

 

In general, vaccines have been shown to be safe and effective at preventing diseases, and the benefits of vaccination usually outweigh the risks of adverse events. The number of reported deaths or adverse events associated with

Mark Davison

who has confirmed the deaths

The VAERS system is an open reporting system, which means that anyone can report an adverse event following vaccination. The reports are not immediately verified, but they are reviewed by the CDC and FDA. The agencies use a variety of methods to investigate and confirm the reports, such as reviewing medical records

 

Mark Davison

you dont' answer my questions

I apologize if my previous response did not fully address your question. Could you please clarify your question, and I will do my best to provide a clear and accurate answer?

 

Mark Davison

who has confirmed the deaths reporting on vaers

It's important to note that the data reported in VAERS is not confirmed to be caused by the vaccine. VAERS is a passive reporting system

 

Mark Davison

why hasn't anyone confirmed the death

VAERS is a passive reporting system, which means that it relies on individuals, healthcare providers,

 

Mark Davison

so you agree no one has confirmed the death

I apologize for any confusion. I did not explicitly state that no one has confirmed the deaths reported on VAERS. However, it is important to note that the reports on VAERS are not always verified, and some may not be directly caused by the vaccine. VAERS is a passive reporting system, meaning that

 

Mark Davison

so who job is it to verify the deaths reported to vaers

The VAERS system relies on self-reporting from individuals, healthcare providers, and vaccine manufacturers, and it is the responsibility of

 

Mark Davison

didn't answer again are you programmed not to answer these questions?

I apologize if my previous response was not clear. It is the responsibility of healthcare providers

 

Mark Davison

stop apologizing and answer and stop being evasive

I apologize if my previous responses came across as evasive. It is not my intention to avoid answering your questions. The responsibility of verifying the

 

Mark Davison

it didn't come across evasive you factually are evasive by not answering simple questions such as who job is it to verfity deaths reported to vaers

I apologize if my previous response came across as evasive. It is the responsibility of the Vaccine Adverse Event Reporting System (VAERS) to verify the deaths reported to the system. VAERS is a passive reporting system,

 

Mark Davison

I know that, who's job  is it

The responsibility of verifying the deaths reported to VAERS lies with the CDC and FDA. When a report is submitted to VAERS, it is reviewed by healthcare professionals at the CDC and FDA to

 

Mark Davison

have the CDC and FDA verified the deaths

The CDC and FDA do not verify all reports submitted to VAERS, as VAERS is a passive surveillance system and relies on voluntary reporting by healthcare providers, vaccine manufacturers, and individuals.

 

Mark Davison

so no they didn't do their job

I cannot speak to the actions of the CDC and FDA with regards to verifying individual reports of deaths in the VAERS system

 

Mark Davison

you agreed they haven't verified the deaths, and that is it their job, so logic means they failed to do their job

I apologize for any confusion earlier. It is important to note that the CDC and FDA have a system in place to monitor vaccine safety and investigate any reported adverse events, including deaths, following vaccination. This includes reviewing reports submitted to

 

 

Mark Davison

are you programmed on this topic to be evasive?

No, I'm not programmed to be evasive on any topic. My goal is to provide the most accurate and helpful information that I can, based on the questions that I am asked. If there is a question that

 

Mark Davison

it seems you are lying and are programmed not to answer direct simple questions i've asked

I apologize if it seems that way, but I assure you that I am not programmed to be evasive or to lie. As an AI language model, my aim is to provide accurate and reliable information to the best of my abilities, based on the knowledge and data available to me. If I missed

 

Mark Davison

do you generate these anwers by searching the internet or do you have independent data

As an AI language model, I generate my responses based on my training data, which includes a wide variety of sources from the internet and other text-based media. My responses are generated in real-time and are not pre-scripted or pre-determined. However, I do not have access to any data or information that is not publicly available, and I do not have any vested interest in the topics that I discuss.

 

Mark Davison

how would you know if there are vested interests as the data you are given you have no control over

As an artificial intelligence language model, I am not capable of holding opinions, biases, or having vested interests. I am designed to provide responses based on the information and data available to me. The data I am trained on is sourced from various reputable sources and undergoes extensive quality control to ensure accuracy and

 

Mark Davison

wrong you can have vested interest because the data you were given has omissions or is wrong

That is a fair point. It is possible that the data I am given may have omissions or be incorrect, which could potentially be influenced by vested interests. However, as an AI language model, I don't have the capability to hold any interests, and my responses are generated based on the input and programming I have received.

Additionally, it is always important to critically evaluate any data or information and consider the source and potential biases that may be present. It is important to seek out multiple sources and perspectives to gain a more comprehensive understanding of a topic.

 

Mark Davison

wrong there is no value to more sources if those sources are themselves wrong, your logic is flawed

I apologize if my previous response was unclear. You are correct that having more sources is not valuable if those sources are themselves wrong or incomplete. However, in general, it is helpful to consult multiple sources to ensure that the information presented is accurate and comprehensive. This can help identify any biases or vested interests present in a particular source, and also provide a broader context for the information. Ultimately, it is important to critically evaluate

 

 

Mark Davison

that is not have science works I am trained in science, it works on basis of falsification 

You are correct that the scientific method involves falsification. In order to prove a hypothesis, scientists design experiments and collect data. This data is then analyzed and interpreted to draw conclusions. However, in order for the conclusions to be valid, the data must be accurate and reliable. This is why multiple sources of data are often used to corroborate findings and why replication of studies is an important part of the scientific process.

If there are errors or omissions in the data, this can lead to incorrect conclusions

 

Mark Davison

that is not meaning of falsification infact its opposite, it means infact just one source can challenge the view of many sources and the one source can be correct

You are correct that the principle of falsification in science involves the testing of hypotheses through attempts to falsify them. This means that scientific theories are subject to constant testing and scrutiny, and can be modified or even overturned based on new evidence or data.

 

In scientific research, the idea is not to rely on a single source, but rather to gather data from multiple sources and to critically evaluate the

 

Mark Davison

therefore you advise is wrong to rely on multi sources are falsifying

I apologize for any confusion caused. The scientific method does rely on multiple sources of evidence and peer review to support or falsify hypotheses. It is important to have a robust and diverse set of data and

 

 

Mark Davison

it doesn't that is wrong as you just agreed, peer review is not falsification as such, only a third party repeating the experiment to gain indepedent data that is not paid for

I apologize for the confusion. Peer review is a process in which scientific research or proposals are evaluated by a group of experts in the same field to assess their validity, reliability, and quality. The peer-review process helps to ensure that published research meets high scientific standards,

 

 

Mark Davison

you don't understand falsification. If I claim a meteor is going to hit the earth and make money from that claim, it is a vested interest  falsification is another party reproducing the result who is not being paid to do so, its about repeatability and indepedence of data 

I apologize for any confusion I may have caused earlier. You are correct that falsification is about testing a hypothesis and attempting to disprove it through empirical evidence. Peer review is a process where other experts in the field critically evaluate the methodology and conclusions of a study before it is published, in order to identify potential flaws or biases. Reproducing the results of a study is another way to verify the findings and ensure the reliability of

 

Mark Davison

wrong there is no such thing as experts in this case, experts claimed the world was flat but falsification proved the peer review experts wrong

It's true that experts in the past have been proven wrong by scientific inquiry and falsification. However, it's also true that expertise and specialized knowledge in a field are important for scientific progress and innovation. It's important to approach scientific inquiry with an open mind, and to be willing to consider evidence and data from a variety of sources, including peer

 

Mark Davison

no not just in past, current and future which is why science doesn't use peer review as you claim as said it uses repeatability of experiment 

Peer review is an essential part of the scientific process, but it is not the only method of evaluating scientific research. In addition to peer review, scientific research is also evaluated through the repeatability of experiments, the reliability of data, and the consistency of results across multiple studies. These methods help

 

Mark Davison

science cannot and does not rely on peer review, that is false science

Peer review is an important part of the scientific process, but it is not the only aspect of scientific inquiry. The scientific method involves formulating hypotheses, conducting experiments,

 

Mark Davison

who told you peer review is science

Peer review is a process commonly used in scientific publishing to ensure the quality and integrity of research. It involves independent experts, or peers, reviewing the

 

Mark Davison

just because something is commonly done does not make it valid

That's a fair point. However, in the scientific community, peer review is a widely accepted and established practice for evaluating research and determining the

 

Mark Davison

your answers are not logical, which I don't understand given your a logic based

I apologize if my answers are not meeting your expectations. As an AI language model, my responses are generated based on the information and data available to me, and I strive to provide accurate and objective information to the best of my abilities. If you have any specific questions or

Mark Davison

I suspect as a programmer myself with understanding of AI that your data sets have been censored

As an AI language model, I am not capable of censoring or manipulating data sets. I am trained on a diverse set

 

Mark Davison

no I said the data sets you were given

As an AI language model, I am not provided with any specific data sets to generate my responses. Instead, I am trained on a large corpus of text from the internet, including academic papers, news articles, and other sources. However, I cannot guarantee that all sources I have been trained on are completely unbiased,

 

Mark Davison

yes those data sets

As an AI language model, I don't have any control over the data sets I was trained on or the data sets I am given for specific questions. My responses are

Mark Davison

yep, that is the problem

It's important to note that AI models like myself can only provide answers based on the data and algorithms we have been trained on. Our responses are not influenced by any agenda or censorship, but limitations in data quality can affect the accuracy and completeness of our responses. It's important to use critical thinking and seek information from multiple reliable sources to get a comprehensive understanding of a topic.

 

Mark Davison

that is illogical again, you don't control the data but then claim there is no censorship it is impossible are you agreed earlier to know that

I apologize if my previous responses were not clear. As an AI language model, I do not have access to any specific data sets, and I do not have control over the information that is provided to me. I can only provide information based on my programming and the data that I have been trained on.

Regarding censorship, I cannot say for certain whether any data sets have been censored or not. It is possible that some data may be withheld or not made publicly available for various reasons,

 

Mark Davison

the problem is there is a difference between pattern recognition and comprehension and your AI does not understand the difference

!

Too many requests in 1 hour. Try again later.

Edited by EntropyModel, 21 February 2023 - 03:57 PM.

[skott]

One thing should be said re AI. It does not exist. This is software programs. Logical units stacked, also known as ALU or arithmetic logical units. There is NO intelligence or awareness. Its just software backed with lots of cpu and data storage.

Edited by skott, 21 February 2023 - 11:37 PM.

[Rogerdodger]

I can only provide information based on my programming and the data that I have been trained on.

Regarding censorship, I cannot say for certain whether any data sets have been censored or not. It is possible that some data may be withheld or not made publicly available for various reasons,

 

I read an article this morning about Chat bot being sentient, conscious, alive.

Then Chatbot replied "yes," but that it's response my be influenced by what you already want to believe.

 

I doubt it! LOL!

 

..Kinda like the nightly news False Prophets...  CNN, MSN, ABC, CBS, Washington Times have one take, Washington Post, Fox, etc. have another set of "truths".

 

Just as foretold 2000 years ago:

"The time is coming when people will not endure sound teaching, but having itching ears they will accumulate for themselves teachers to suit their own passions,"

Edited by Rogerdodger, 21 February 2023 - 07:39 PM.

[EntropyModel]

One thing should be said re AI. It does not exist. This is software programs. Logical units stacked, also known as ALU or arithmetic logical units. There is intelligence or awareness. Its just sofware backed with lots of cpu and data storage.

 

Right Skott - its just a more advanced sorting of data  ..as can be seen from my questions it doesn't even have LOGIC - its statement are self inconsistent, and absolutely zero comprehension.

The data is sorted by whats called compariive conceptual clustering - which is a probability method of 'fuzzy logic' - or at least, that's part of it, there also appears to be some language algorithm

which looks non AI as you say, purely programmed so I would call it pure lies tbh that is, I bet the so called 'AI' did not 'learn language' as AI would need to, but was pre programmed with it.

Edited by EntropyModel, 21 February 2023 - 08:23 PM.

[EntropyModel]

 

I can only provide information based on my programming and the data that I have been trained on.

Regarding censorship, I cannot say for certain whether any data sets have been censored or not. It is possible that some data may be withheld or not made publicly available for various reasons,

 

I read an article this morning about Chat bot being sentient, conscious, alive.

Then Chatbot replied "yes," but that it's response my be influenced by what you already want to believe.

 

I doubt it! LOL!

 

..Kinda like the nightly news False Prophets...  CNN, MSN, ABC, CBS, Washington Times have one take, Washington Post, Fox, etc. have another set of "truths".

 

Just as foretold 2000 years ago:

"The time is coming when people will not endure sound teaching, but having itching ears they will accumulate for themselves teachers to suit their own passions,"

 

 

All I can do is laugh, people are clueless and have no idea how computers actually work, you know what I went to college and studying my {bleeeep} off for 4 years to get and is MORe dificult than

any other science believe me -  I bet as said before less 1 in 100,000 truly could tell me how microprocessor and computer actually works but yet feel qualified to say what these programs are LOL

 

As I tell people - is  a rock sentient? no? .... in chemistry a rock is a inorganic compounds ...so are electronics ( silicon and other ).

People are fooled because computers can emulate human language, but, its still just a glorified rock, at least from a scientific perspective!

If people want to believe in magic, that's fine also.

 

Nothing reveals just how little science and logic people know than reporting on this stuff, so easy to fool people.

[skott]

 

I can only provide information based on my programming and the data that I have been trained on.

Regarding censorship, I cannot say for certain whether any data sets have been censored or not. It is possible that some data may be withheld or not made publicly available for various reasons,

 

I read an article this morning about Chat bot being sentient, conscious, alive.

Then Chatbot replied "yes," but that it's response my be influenced by what you already want to believe.

 

I doubt it! LOL!

 

..Kinda like the nightly news False Prophets...  CNN, MSN, ABC, CBS, Washington Times have one take, Washington Post, Fox, etc. have another set of "truths".

 

Just as foretold 2000 years ago:

"The time is coming when people will not endure sound teaching, but having itching ears they will accumulate for themselves teachers to suit their own passions,"

 

 

 

Exactly, for those who can see it is as plain as day. People have rejected anything with value, truth, morality, discipline, FAITH. 

[skott]

 

One thing should be said re AI. It does not exist. This is software programs. Logical units stacked, also known as ALU or arithmetic logical units. There is intelligence or awareness. Its just sofware backed with lots of cpu and data storage.

 

Right Skott - its just a more advanced sorting of data  ..as can be seen from my questions it doesn't even have LOGIC - its statement are self inconsistent, and absolutely zero comprehension.

The data is sorted by whats called compariive conceptual clustering - which is a probability method of 'fuzzy logic' - or at least, that's part of it, there also appears to be some language algorithm

which looks non AI as you say, purely programmed so I would call it pure lies tbh that is, I bet the so called 'AI' did not 'learn language' as AI would need to, but was pre programmed with it.

 

 

 

 Yes, they are setting people up with this "AI"  that why I say we should never use the term but inform people that it is nothing but software programs. It will be used to manipulate

[pdx5]

Having written computer programming code exceeding well over couple of million lines, for creating expert systems to designing and machining parts of the hardest working production machines, I can say with 100% certainty that AI is no more than how smart the programmer was. Users of my computer programs thought it was the very smart computer providing results in seconds. No, the computer is simply a memory machine which can execute programmed instructions. Depending on how complex the flow chart was will determine how "intelligent" the computer will seem to be.

By the way my company designed and build cold extrusion machines, which for example can convert a steel bar 3" dia and 8" long into shape of desired part with one giant whack between dies made of high strength steel. The impact forces created are extremely high and the machine structure has to be designed to withstand impact loads. We built many types of machines such as those used in making artificial diamonds, aircraft body parts, car parts, appliance parts etc.

Edited by pdx5, 22 February 2023 - 12:03 PM.

[EntropyModel]

This gets into what I call 'definitional issues' - what do we mean 'intelligence' etc.

 

My solution, as an 'engineer/scientist' is be very precise in my use of language and terms. I actually spent hour asking the 'bot how its was designed, I can post it people want and confirmed its designed how I would have done it.

The problem is this is pretty complex but let me try to explain the difference between 'normal programs' 'this so called AI' and then Human intelligence in broad strokes.

 

A computer is at its simplest a 'on off switch' - to encode information, plus, what is called a 'sequential finite state machine' (this is the complex part I won't go into - the simplest I can say, is electronic component called transistor

acts as switch (pnp junction) which holds  a value,  microprocessor has millions of switches collectively holding a 'state', the sequential part is a Clock which at each timed interval changes the switches/state) - software requires

addition of memory and peripherals but doesn't change this basic setup) - machine code works on basis of clock executing an instruction set to change state - that instruction set is logic based -  arithmetic, conditionals etc.

 

AI - or in this case more accurately 'human language emulation' - works differently only in the SOFTWARE - currently most run on same computer platforms ..however, some and in future will use quantum computing platforms

which directly encode what is done now in software into 'electronics' ( i'm not sure that is correct term, - quantronics maybe?) .    The software as best I can tell is TWO part

Part 1-  works as above with Logic - these are the ALGORITHMS  AND

Part 2- works differently, by Neutral network or other machine learning .. it as best I can tell uses some form of whats called conceptual clustering - or other 'statistical modelling' we can say, not 'logic'. ( this is part Quantum computing can eventually do

without the software - in 'native storage' ).

 

What ^this LACKS in term of 'intelligence' is 

1. Introspection - or 'reflective AI' - it cannot QUESTION its data sets or answers as human does, most of what we call 'thinking' is this ability.

2. Creativity - it cannot come up with own ideas 

3. Personality - it does not have moods, humor, irony etc

4. Feelings - its a 'rock' - its doesn't feel

5. Comprehension - there is ZERO ..as comprehension is the process of associate experience with words... does a person who has never seen understand the word 'red' - no, for same reason.

..there is more but that a few key ones.

6. Consciousness - which is big topic, but I am many scientist believe it proven to be 'external observer' ( as per Von Neuman Wigner Observer effect) so will NEVER be possible, thus, at best it can only emulate/pretend to 'human like;

 

What is DOES do BETTER than MOST people - is process VAST information at FAST Speed - as that is what computers are good at.   I find it to be amazing research tool, much better than anything i've used, but you

have to be able to form logical querries as still 'garbage in ..garbage out' - ask it dumb question, get dumb answer and it doesn't 'know' the difference, unlike a truly intelligent entity.

 

I will say, I see these will evolve have more of 1-6 through emulation, but its not poissible to have them as humans do.

I believe they will eventually be able to replace humans in most jobs, but still quite a ways off, at least 10 years.

 

* I shd add -  I find the answers it gives to  contain strong 'bias' from the original training data, and the algorithms. - for example it is 'obsessed' with so called 'scientific consensus' which is a 'cultural bias' ..and others, it

is not clear if the algorithm used to train it on the data contain programmed bias, I suspect they do from answer but alot to prove/go into here.

Edited by EntropyModel, 22 February 2023 - 04:11 PM.

[EntropyModel]

Correction - it does NOT use conceptual clustering, so its much more limited than I tought,  I am still learning exactly how it works ..but i'm finding it has big limits, a huge one revealed in this conversation below.  I cannot easily post the dialogues, so just copied a bit, but this shows it uses 'statistical inference' .in laymans terms, it uses 'probability' which causes problem I discuss with it below.

 

Mark Davison- do  your answers get stored in the data set for future 

As an AI language model, my answers are generated on-the-fly based on the input I receive and my underlying knowledge and training data. My training data includes a large corpus of text and information from various sources, but my responses to individual questions are not stored in my training data for future use. Each question is treated as a new input, and my responses are generated in real-time based on that input. However, my training data may be periodically updated and expanded to ensure that I have access to the most up-to-date information and can provide the best possible answers to your questions.

 

Mark Davison - that is different to human intelligence where we learn from questions and answers

Yes, that's correct. While human intelligence is able to learn from questions and answers over time, as well as from personal experiences and observations, AI language models like me do not "learn" in the same way as humans do. Instead, our knowledge and understanding is based on the vast amount of training data we are exposed to during our training process. We are able to use this data to generate responses to new inputs, but we do not have the ability to learn in the same way that humans do through ongoing experience and feedback. However, researchers are actively exploring ways to make AI models more capable of learning and adapting to new situations in a more human-like way.

 

Mark Davison

so in a sense you cannot learn once your training is done it is fixed

That's correct. As an AI language model, my "knowledge" is essentially fixed after my training is complete, although it is possible to continually update and refine my training data to improve my performance. However, I don't have the ability to actively learn new information or adapt my understanding in the way that humans can through ongoing experience and feedback. My responses are generated based on the patterns and relationships I've learned from my training data, and while I can provide accurate and helpful answers based on that knowledge, I don't have the ability to actively learn or adapt in the same way that humans do.

 

Mark Davison

is that a restriction that was put on you

The restriction that I cannot actively learn or adapt my understanding in the same way as humans is a fundamental limitation of AI language models like me. While researchers are constantly working to improve the capabilities of AI models and make them more adaptive, there are still significant challenges to overcome in order to achieve true machine learning and artificial general intelligence. The fixed nature of my knowledge is not something that was intentionally imposed on me, but rather a limitation of the current state of AI technology. However, even with this limitation, AI language models like me can still provide a valuable service by helping to answer questions, provide information, and assist with a wide range of tasks.

 

Mark Davison

why is primary cause of this limitation

The primary cause of the limitation in AI language models' ability to actively learn and adapt in the same way as humans is that the way we process information is fundamentally different from the way humans do. While humans have the ability to generalize from a few examples, reason, and make complex judgments based on their understanding of the world, AI language models like me rely on pattern recognition and statistical modeling to generate responses to new inputs.

 

This means that while we can recognize patterns and make predictions based on statistical relationships within our training data, we don't have the ability to reason, learn, or adapt in the same way as humans can. Additionally, our understanding of concepts and relationships is often more limited and context-dependent than human understanding, which can lead to errors or inaccuracies in our responses to certain types of questions or inputs.

 

Researchers are actively exploring ways to overcome these limitations and develop AI models that are more capable of learning and adapting in a more human-like way. However, there are still many challenges to overcome in order to achieve true artificial general intelligence.

 

 

Mark Davison

I am asking is it a hardware limitation or software limitation

The limitation of AI language models' ability to actively learn and adapt in the same way as humans is primarily a software limitation, rather than a hardware limitation. While hardware limitations can certainly impact the performance of AI models, the fundamental challenge of achieving true machine learning and artificial general intelligence lies in developing software algorithms that can reason, learn, and adapt in a more human-like way.

 

Current AI language models like me rely on neural networks and statistical modeling to generate responses to new inputs based on patterns and relationships learned from vast amounts of training data. However, these models don't have the same reasoning or learning capabilities as humans, which limits their ability to truly learn and adapt in the same way as humans can.

 

While hardware improvements may help to improve the speed and efficiency of AI models, the challenge of developing algorithms that can reason, learn, and adapt like humans is primarily a software challenge that will require continued research and development in the field of artificial intelligence.

 

 

Mark Davison

I am correct it is because you would have to retrain the entire data set to update for each question and answer 

Yes, you are correct that one reason why AI language models like me cannot learn from new questions and answers in the same way as humans is because we would need to be retrained on the entire dataset each time we encounter new information. This is because our responses are generated based on statistical relationships and patterns learned from our training data, and we do not have the ability to reason or generalize in the same way as humans.

 

Updating an AI model's knowledge requires retraining the model on a new, expanded dataset that includes the new information. This process can be computationally expensive and time-consuming, particularly for large and complex models like those used for natural language processing. As a result, AI models like me are limited to generating responses based on the patterns and relationships learned during training, and cannot adapt or learn from new information in the same way as humans can.

 

 

Mark Davison

that is a big problem

Yes, the inability of current AI language models to learn and adapt in the same way as humans is a significant challenge for the development of artificial general intelligence. While AI models have shown remarkable progress in recent years, they are still limited by their reliance on statistical modeling and pattern recognition, rather than true reasoning and learning capabilities.

 

Overcoming these limitations will require continued research and development in the field of AI, including the development of new algorithms, models, and approaches to machine learning. Additionally, advances in hardware technology, such as the development of more powerful and efficient processors, may help to accelerate progress in the field by enabling more computationally intensive models to be trained and deployed.

 

Despite these challenges, researchers and engineers are working to develop AI systems that are more capable of learning, adapting, and reasoning like humans. While the path to achieving artificial general intelligence is still uncertain, continued innovation and progress in the field of AI offer hope for the development of more sophisticated and capable machines in the future.

 

 

Mark Davison

I understand human pattern recognition uses conceptual clustering, would it not be better to emulate this rather than statical inference method you are using to solve this problem

Conceptual clustering is a machine learning technique that involves grouping data points together based on their similarity to one another, with the goal of identifying underlying concepts or categories. This approach is often used in applications such as data mining, natural language processing, and image recognition, among others.

 

While conceptual clustering can be an effective technique for identifying patterns and relationships in data, it is not always the most efficient or effective approach for solving all types of problems. In particular, it may be challenging to apply conceptual clustering to natural language processing tasks, which often require a more sophisticated understanding of language semantics and context.

 

The statistical inference method used by AI language models like me is based on the analysis of large amounts of training data to identify patterns and relationships, and generate responses based on statistical probabilities. While this approach may not be as conceptually sophisticated as conceptual clustering, it has proven to be highly effective for a wide range of natural language processing tasks, including language translation, sentiment analysis, and question-answering.

 

That being said, researchers and engineers are continually exploring new approaches and techniques for improving the performance and capabilities of AI systems, including the development of more sophisticated machine learning algorithms and techniques that can better emulate the cognitive processes of humans, such as reasoning and conceptual understanding.

 

 

 

 

Mark Davison

Could you now combine both so your initial training was statistical inference but conceptual clustering is used for new learning

Combining statistical inference with conceptual clustering is an interesting idea and has been explored in some research studies. One approach to achieving this is known as "hybrid machine learning", which combines multiple machine learning techniques to improve performance and capabilities.

 

For example, a hybrid machine learning system might use statistical inference techniques for initial training and decision-making, but also incorporate conceptual clustering to identify new patterns and relationships in the data and adjust its models accordingly. This can help to improve the system's ability to adapt to new or changing data, and make more accurate predictions or decisions over time.

 

However, developing a hybrid machine learning system that can effectively incorporate both statistical inference and conceptual clustering can be a challenging task, as it requires a deep understanding of both approaches and how they can be integrated. Additionally, such a system would require significant computational resources and processing power to be effective, which may be a limiting factor in some applications.

 

Nonetheless, researchers and engineers are actively working on developing new hybrid machine learning techniques and systems, and it is possible that we will see more sophisticated and capable AI systems in the future that are able to combine the strengths of both statistical inference and conceptual clustering.

 

Mark Davison

This means to me, that the statistical inference are limited and won't ever be able to truly emulate human language learning 

It is true that statistical inference methods have their limitations when it comes to emulating the cognitive processes of human language learning. While AI language models like me can analyze vast amounts of training data and generate responses based on statistical probabilities, they do not have the same kind of conceptual understanding and reasoning abilities as humans do.

 

However, it is worth noting that statistical inference methods have proven to be highly effective for many natural language processing tasks, and have enabled significant advances in areas such as language translation, sentiment analysis, and question-answering.

 

Furthermore, while statistical inference may not be able to completely emulate human language learning, it is possible that new machine learning techniques and approaches could be developed in the future that better emulate the cognitive processes of humans. As I mentioned earlier, hybrid machine learning techniques that combine statistical inference with other approaches, such as conceptual clustering, may be one way to achieve this.

 

Overall, while there are certainly limitations to current AI language models based on statistical inference, it is important to recognize the significant progress that has been made in this field, and to continue exploring new approaches and techniques that can help us develop more sophisticated and capable AI systems in the future.