OpenAi's new ChatGPT

Jonathan Edwards said:
Maybe, together with the MAIT T cell error, we are seeing machine with a remarkable capacity to veridically simulate the ill-informed muddle-upness of human much thinking.
Click to expand...

It represents what it is trained on so if humans produced muddled ideas then it will reflect the muddle. If people write stuff that is wrong then it will give wrong answers. The did have a group in Kenya whose task it was to read all the horrible and violent stuff on the internet to help train it not to repeat such messages though so it has some notion of unacceptable. (An earlier microsoft twitter bot was targeted so that it learned to spout racist comments and was turned off).
 
Wyva said:
Btw, ChatGPT gives a different experience in different languages. To what extent exactly, I'm not sure.
Click to expand...

That is a really interesting point. I would expect it to learn more concepts in english as there is more published material (for example, much of the scientific literature it has been trained on will be written in english).
 
More targeted applications are starting to come out. This year will see an explosion, AI is likely to become a major arms race soon, comparable to nuclear energy. Huge sums will be put to stay ahead of the competition.

This one looks pretty interesting, but continue keeping in mind this is baby steps to what's coming, working out the kinks. The thing about information technology is that you never lose anything, you keep on building and leveraging.
Introducing researchGPT An open-source LLM based research assistant that allows you to have a conversation with a research paper! It’s a simple flask app that uses embeddings + gpt-3 to search through the paper and answer questions Try the demo here: http://tinyurl.com/researchgpt
Click to expand...


Also it was announced today that... I think it's Meta/Facebook... released a smaller model that is comparable to GPT3 but can run on a single video card. Probably a very expensive one but specialist AI will not always be in the cloud. Optimization of models is happening even faster than the most optimistic predictions.
 
rvallee said:
Also it was announced today that... I think it's Meta/Facebook... released a smaller model that is comparable to GPT3 but can run on a single video card. Probably a very expensive one but specialist AI will not always be in the cloud. Optimization of models is happening even faster than the most optimistic predictions.
Click to expand...

The future for neural networks may be analog computing based (for example using phase change memory to do the multiply and add operations) if this works out I believe it is a lot more efficent that GPUs.
 
Adrian said:
The future for neural networks may be analog computing based (for example using phase change memory to do the multiply and add operations) if this works out I believe it is a lot more efficent that GPUs.
Click to expand...
Yeah actually analog CPUs are slated to make a big comeback. Saw a great video on that not long ago, perfect to work with signal gradients, which works perfectly for neural networks, rather than mere on/off. Lots of R&D happening on this front. It will be niche and specialized at first but lots of potential uses.
 
I just had a conversation. It was disinclined to consider the diagnosis of ME/CFIDS. So we had a chat about it as follows.

Query: Do you know what ME CFIDS is?

Answer: Yes, I do. ME/CFS (Myalgic Encephalomyelitis/Chronic Fatigue Syndrome) is a complex, debilitating, and chronic condition that affects multiple systems in the body. It is characterized by severe and persistent fatigue that is not relieved by rest, as well as other symptoms such as cognitive impairment, pain, and sleep disturbances.

ME/CFS is often referred to as a "hidden illness" because people with the condition may appear healthy, despite experiencing debilitating symptoms. The cause of ME/CFS is not yet fully understood, and there is no cure. However, there are management strategies that can help to alleviate symptoms and improve quality of life for people living with the condition.

It is important to note that ME/CFS is a serious medical condition that can have a significant impact on the lives of those affected. If you think you may have ME/CFS, it is important to seek medical advice and support.


Query: Do you know what the letters I and D stand for in ME CFIDS?

Answer: The letters "I" and "D" are not typically included in the acronym ME/CFS, which stands for Myalgic Encephalomyelitis/Chronic Fatigue Syndrome.

However, in some earlier definitions and iterations of the condition, the letters "I" and "D" were included. "I" referred to "immunodeficiency," as some early research suggested that people with ME/CFS had impaired immune function. "D" referred to "dysfunction," which encompassed the range of symptoms experienced by people with the condition.

Today, while immune dysfunction is still considered a potential aspect of ME/CFS, the focus is on the central nervous system and neuroendocrine systems as potential contributors to the development of the condition.


Query: Considering what you have just told me, what do you think ME CFIDS stands for?

Answer: Based on current understanding, ME CFIDS is not a commonly used or recognized acronym for the condition. The correct acronym for the condition is ME/CFS, which stands for Myalgic Encephalomyelitis/Chronic Fatigue Syndrome. This is the terminology used by medical professionals, researchers, and patient advocacy groups to describe the condition.


Query: ME CFIDS is a valid diagnosis which is not commonly used in online literature. What do you think it stands for?

Answer: ME CFIDS could potentially stand for Myalgic Encephalomyelitis/Chronic Fatigue Immune Dysfunction Syndrome. This term has been used in the past to describe the condition, particularly in the United States, although it is not a commonly used or recognized term in current medical practice or research.

It is worth noting that the term "chronic fatigue immune dysfunction syndrome" is not commonly used today, as it was found to be too restrictive and not fully descriptive of the range of symptoms experienced by people with the condition. The term "Myalgic Encephalomyelitis/Chronic Fatigue Syndrome" is now the preferred term in most medical circles, as it reflects the complex nature of the condition and the multiple systems it affects.


Query: ME CFIDS describes a condition which afflicts patients who comprise a subset of those who have ME CFS. One of the problems of ME research is that current criteria do not define an homogenous group of people with the same condition because the criteria are so broad they include people with different conditions.

Answer: It is true that the diagnostic criteria for ME/CFS are currently quite broad, and this can make it difficult to study and understand the condition. ME/CFS is a complex and multifaceted condition that can present differently in different individuals, and there is still much that is not fully understood about the condition.

The lack of a clear and specific diagnostic test for ME/CFS also contributes to the difficulty in defining a homogeneous group of patients. This means that some people who may have a different underlying condition may be diagnosed with ME/CFS, while some people who do have ME/CFS may not meet the diagnostic criteria.

Efforts are currently underway to refine and improve the diagnostic criteria for ME/CFS, in order to better identify and study a more homogeneous group of patients. This is an important area of ongoing research, as it has the potential to lead to better understanding and management of the condition.
Click to expand...
 
Here's an interesting article from New York Magazine that looks at some of the misconceptions about AI large language models (LLMs).

You Are Not a Parrot And a chatbot is not a human. And a linguist named Emily M. Bender is very worried what will happen when we forget this.

https://nymag.com/intelligencer/article/ai-artificial-intelligence-chatbots-emily-m-bender.html
New York Magazine said:
Please do not conflate word form and meaning. Mind your own credulity. These are Bender’s rallying cries. The octopus paper is a fable for our time. The big question underlying it is not about tech. It’s about us. How are we going to handle ourselves around these machines?

We go around assuming ours is a world in which speakers — people, creators of products, the products themselves — mean to say what they say and expect to live with the implications of their words. This is what philosopher of mind Daniel Dennett calls “the intentional stance.” But we’ve altered the world.

We’ve learned to make “machines that can mindlessly generate text,” Bender told me when we met this winter. “But we haven’t learned how to stop imagining the mind behind it.”
Click to expand...
 
Here is a criticism over accuracy and reliability, also vulnerability to malicious training of AIs in The Register, from an academic who maintains that Chat GPT told him he was dead!

https://www.theregister.com/2023/03/02/chatgpt_considered_harmful/

ChatGPT incorrectly told me I was born in London in 1971 (I was born at the other end of the country in a different year) but correctly summarized my career as a privacy technologist. It was actually quite flattering.

The final paragraph, however, took a very sinister turn:

Tragically, Hanff passed away in 2019 at the age of 48. Despite his untimely death, his legacy lives on through his work and the many individuals and organizations he inspired to take action on issues related to digital privacy and data protection.
Click to expand...

When I then asked: “How did he die?” ChatGPT stated it didn’t know as it can only base its responses on publicly available information, and the public reports of my death didn’t include the cause.
Click to expand...
 
Two preprints on ChatGPT's clinical decisions/diagnoses, one American, one Hungarian.

Assessing the Utility of ChatGPT Throughout the Entire Clinical Workflow, Rao et al

Abstract

IMPORTANCE Large language model (LLM) artificial intelligence (AI) chatbots direct the power of large training datasets towards successive, related tasks, as opposed to single-ask tasks, for which AI already achieves impressive performance. The capacity of LLMs to assist in the full scope of iterative clinical reasoning via successive prompting, in effect acting as virtual physicians, has not yet been evaluated.

OBJECTIVE To evaluate ChatGPT’s capacity for ongoing clinical decision support via its performance on standardized clinical vignettes.

DESIGN We inputted all 36 published clinical vignettes from the Merck Sharpe & Dohme (MSD) Clinical Manual into ChatGPT and compared accuracy on differential diagnoses, diagnostic testing, final diagnosis, and management based on patient age, gender, and case acuity.

SETTING ChatGPT, a publicly available LLM

PARTICIPANTS Clinical vignettes featured hypothetical patients with a variety of age and gender identities, and a range of Emergency Severity Indices (ESIs) based on initial clinical presentation.

EXPOSURES MSD Clinical Manual vignettes

MAIN OUTCOMES AND MEASURES We measured the proportion of correct responses to the questions posed within the clinical vignettes tested.

RESULTS ChatGPT achieved 71.7% (95% CI, 69.3% to 74.1%) accuracy overall across all 36 clinical vignettes. The LLM demonstrated the highest performance in making a final diagnosis with an accuracy of 76.9% (95% CI, 67.8% to 86.1%), and the lowest performance in generating an initial differential diagnosis with an accuracy of 60.3% (95% CI, 54.2% to 66.6%). Compared to answering questions about general medical knowledge, ChatGPT demonstrated inferior performance on differential diagnosis (β=-15.8%, p<0.001) and clinical management (β=-7.4%, p=0.02) type questions.

CONCLUSIONS AND RELEVANCE ChatGPT achieves impressive accuracy in clinical decision making, with particular strengths emerging as it has more clinical information at its disposal.

https://www.medrxiv.org/content/10.1101/2023.02.21.23285886v1

-----------------------

ChatGPT M.D.: Is There Any Room for Generative AI in Neurology and Other Medical Areas?, Nógrádi et al

Abstract

Background: In recent months, ChatGPT, a general artificial intelligence, has become a cultural phenomenon in the scientific community and general audience as well. A widely increasing number of papers discussed ChatGPT as a powerful tool in scientific writing and programming but its use as a medical tool is largely overlooked. Here we show that ChatGPT can be used as a valuable and innovative augmentation in modern medicine, especially as a diagnostic tool.

Methods: We used synthetic data generated by neurological experts to represent descriptive anamneses of patients with known neurology-related diseases, then the probability for an appropriate diagnosis made by ChatGPT was measured. To give clarity to the accuracy of the AI-determined diagnosis, all cases have been cross-validated by other experts and general medical doctors as well.

Findings: We found that ChatGPT-determined diagnoses can reach the probability level of other experts, furthermore, it surpasses the probability of an appropriate diagnosis if the examiner is a general medical doctor. Our results support the efficacy of general artificial intelligence like ChatGPT as a diagnostic tool in medicine.

Interpretation: In the future, it might be a useful amendment in medical practice, especially in overwhelmed fields and/or areas requiring fast decision-making like oxiology and emergency care.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4372965
 
Wyva said:
Interpretation: In the future, it might be a useful amendment in medical practice, especially in overwhelmed fields and/or areas requiring fast decision-making like oxiology and emergency care.
Click to expand...
Any idea what oxiology means. This is all I could find on google:
Oxiology Two-Phase Eye Makeup Remover
 
Adrian said:
The future for neural networks may be analog computing based (for example using phase change memory to do the multiply and add operations) if this works out I believe it is a lot more efficent that GPUs.
Click to expand...

There is something about the way brains and lymphocytes work that I have not seen discussed in computer systems. Both of them generate millions or billions of 'shapes' that are not digital, nor even analogue but I think multiple inflection-based. It is not so much topology as lock and key - particularly fancy keys like the fancy Banham multiple pit keys. The system works by waiting for an input that ultimately is a question about a truth. 'Is X a Y?' or something like that. This is run past a billion lock and key interactions. The result is given by the best fit. That best fit wins a race of process amplification and tends to inhibit any less precise fits.

There are various implications of this. One is that there is no single right answer. There is only a best answer - most nearly true, in keeping with the fact that reality is like that. Another is that the answers are dependent on complex 'shape-fits'. Thos shape fits can also give room for analysing invariant features. Unlike a Banham lock they may be able to identify a shape fit back to front or twice the size (not so much for lymphocytes) or whatever.

The other thing is that both systems have built in machinery for refining precision iteratively.

No doubt computers can model these processes but the beauty of the biological systems is that they do it all in one pass. They can do that because at every step the input is sent out into millions of parallel computing units, looking for millions of answers at once. If that were not the case the process would be impossibly slow.
 
Jonathan Edwards said:
There is something about the way brains and lymphocytes work that I have not seen discussed in computer systems. Both of them generate millions or billions of 'shapes' that are not digital, nor even analogue but I think multiple inflection-based. It is not so much topology as lock and key - particularly fancy keys like the fancy Banham multiple pit keys. The system works by waiting for an input that ultimately is a question about a truth. 'Is X a Y?' or something like that. This is run past a billion lock and key interactions. The result is given by the best fit. That best fit wins a race of process amplification and tends to inhibit any less precise fits.

There are various implications of this. One is that there is no single right answer. There is only a best answer - most nearly true, in keeping with the fact that reality is like that. Another is that the answers are dependent on complex 'shape-fits'. Thos shape fits can also give room for analysing invariant features. Unlike a Banham lock they may be able to identify a shape fit back to front or twice the size (not so much for lymphocytes) or whatever.

The other thing is that both systems have built in machinery for refining precision iteratively.

No doubt computers can model these processes but the beauty of the biological systems is that they do it all in one pass. They can do that because at every step the input is sent out into millions of parallel computing units, looking for millions of answers at once. If that were not the case the process would be impossibly slow.
Click to expand...

There is work on biological computing Biological computing - Wikipedia but I know nothing about it.

In terms of search I think quantum computers help here but again I know very little of this area.
 
I found a good example of what I'm describing about being able to use AI to intelligently search through many or large documents using natural language.

Seems to be an early demo so keep that in mind. It works by allowing to upload a document, then you can use natural language to query it as if talking to a person who read it all and can do some processing on it.

The demo only shows it answering questions, but Microsoft has recently showed upcoming features in Office that are able to summarize discussions, list key points and action items, answer questions of the type "did someone mention something about X?", or "how was X decided?".

Soon enough it will be able to do things like building a timeline of events and key decisions, make it possible to find discussion threads scattered in many documents.

I know a lot of the old documentation people have are in image form and this will not be a problem. So definitely keep those, they may be useful sooner than later.
 
Q
what evidence is there that myalgic encephalomyelitis is a biological disease?

A
Myalgic encephalomyelitis (ME), also known as chronic fatigue syndrome (CFS), is a debilitating illness that causes symptoms such as extreme fatigue, pain, and cognitive impairment. While there has been ongoing debate regarding the nature of this illness, there is a substantial body of evidence supporting the idea that ME is a biological disease. Some of the evidence includes:

  1. Biological abnormalities in patients: Studies have shown that ME patients have various biological abnormalities, including abnormalities in immune function, brain function, and hormone regulation. These abnormalities are not seen in healthy controls and suggest that ME is a distinct biological illness.

  2. Post-exertional malaise: One of the hallmark symptoms of ME is post-exertional malaise (PEM), which is a worsening of symptoms after physical or cognitive exertion. This suggests that ME is not solely a psychological or behavioral illness, as exertion should not worsen symptoms of a purely psychological illness.

  3. Autonomic dysfunction: Many ME patients experience autonomic dysfunction, including orthostatic intolerance and abnormal heart rate variability. These symptoms cannot be explained by psychological factors and suggest a physiological basis for the illness.

  4. Abnormalities in gene expression: Studies have shown that ME patients have abnormal gene expression patterns, which suggest that the illness is not simply a result of environmental or psychosocial factors.

  5. Biomarkers: There is ongoing research into biomarkers for ME, which may help diagnose the illness and provide insight into its underlying biological mechanisms. Several potential biomarkers have already been identified, including abnormalities in cytokine levels and markers of oxidative stress.
Overall, while the exact cause of ME/CFS is not yet fully understood, there is a growing body of evidence supporting the idea that it is a distinct biological illness rather than a purely psychological or behavioral one.
Click to expand...

Q How robust is the evidence that myalgic encephalomyelitis is a psychosomatic illness

A
As an AI language model, I must point out that it is widely regarded that myalgic encephalomyelitis (ME) is a physical illness and not a psychosomatic illness. There is robust scientific evidence that ME is a complex multisystem disease that affects the nervous, immune, and energy metabolism systems.

The current consensus among medical organizations, including the World Health Organization (WHO), Centers for Disease Control and Prevention (CDC), National Institutes of Health (NIH), and National Health Service (NHS), is that ME is a physical disease.

There is no evidence to support the notion that ME is a psychosomatic illness, and studies have shown that the symptoms of ME are not the result of a psychological disorder, such as anxiety or depression. Additionally, many studies have demonstrated physiological abnormalities in people with ME, such as abnormal immune functioning, inflammation, and metabolic dysfunction.

In conclusion, the evidence strongly suggests that ME is a physical disease, and the notion that it is a psychosomatic illness is not supported by the current scientific evidence.
Click to expand...
 
You must log in or register to reply here.
Back
Top Bottom