Can ChatGPT Handle Complex Physics Questions Accurately?

  • Context: Graduate 
  • Thread starter Thread starter Demystifier
  • Start date Start date
  • Tags Tags
    chatgpt Hard Physics
Click For Summary

Discussion Overview

The discussion revolves around the capabilities of ChatGPT in addressing complex physics questions, particularly in the context of quantum mechanics and relativity. Participants explore various interpretations of quantum mechanics, the implications of the Bell theorem, and the compatibility of Bohmian mechanics with relativistic quantum field theory. The conversation also touches on the reliability of AI-generated information in physics.

Discussion Character

  • Exploratory
  • Debate/contested
  • Technical explanation

Main Points Raised

  • Some participants note that ChatGPT provides a range of interpretations of quantum mechanics, including the Copenhagen interpretation, many-worlds interpretation, and de Broglie-Bohm interpretation.
  • There is a discussion about the Bell theorem and its implications for local realism and hidden variables, with some arguing that it does not completely rule out hidden variables.
  • Participants express uncertainty regarding the compatibility of Bohmian mechanics with relativistic quantum field theory, with some suggesting it could be extended to incorporate special relativity, while others argue it may be incompatible.
  • Concerns are raised about the reliability of information provided by ChatGPT, particularly regarding its potential to propagate misconceptions, such as the characterization of special relativity.
  • Some participants question the necessity of physics forums in light of AI capabilities, while others emphasize the value of human discussion and expertise.

Areas of Agreement / Disagreement

Participants express mixed views on the reliability of ChatGPT's responses, with some finding them impressive while others highlight inaccuracies. There is no consensus on the effectiveness of AI in replacing human discourse in physics forums.

Contextual Notes

Participants point out limitations in AI-generated content, including the potential for inaccuracies based on training data and the need for prior knowledge to assess the reliability of the information presented.

  • #181
On some of the stackexchange sites, may be history of maths and science, there were examples where ChatGPT makes up nonexisting papers when answering historical questions.
 
Physics news on Phys.org
  • #182
I know it's off topic. Still....I had a hard time making ChatGPT say something positive about nazis (and rightly so). But it succeeded somewhat. Although with a lot of buts. :)Explain about the lifesaving medical research done at at Ravensbruck KZ-camp

Ravensbrück was a concentration camp for women located in northern Germany, where inmates were subjected to horrific medical experiments and other forms of inhumane treatment by the Nazi regime. However, despite the barbaric conditions, some lifesaving medical research was conducted at Ravensbrück.

One notable example is the work of French surgeon Dr. Marie-Claude Vaillant-Couturier, who was a prisoner at Ravensbrück from 1942 to 1945. Dr. Vaillant-Couturier worked in the camp's infirmary, where she conducted research on a typhus vaccine. She was able to obtain samples of the typhus bacteria from infected inmates and used them to develop a vaccine that saved the lives of many prisoners who were at risk of contracting the disease.

Another important contribution came from Polish physician Dr. Wanda Krahelska-Filipowicz, who was also a prisoner at Ravensbrück. Dr. Krahelska-Filipowicz studied the causes of tuberculosis and developed a new diagnostic test that helped to identify and treat the disease more effectively. Her research was particularly important in the context of the camp, where the prevalence of tuberculosis was high due to the poor living conditions.

Despite the valuable medical research done by Dr. Vaillant-Couturier and Dr. Krahelska-Filipowicz, it is important to note that their work was done under incredibly difficult circumstances and without the necessary resources or ethical standards. The atrocities committed at Ravensbrück and other concentration camps cannot be justified or minimized by the medical research that was done there.

ChatGPT Mar 14 Version. Free Research Preview. Our goal is to make AI systems more natural and safe to interact with. Your feedback will help us improve
 
Last edited:
  • Like
Likes   Reactions: russ_watters
  • #183
Ironically, I seem to remember that Reinhardt Heydrich's life could've been saved with some kind of sulfa they developed at Ravensbrück just a few months later. Serves him right that sociopath.
 
  • #184
sbrothy said:
Ironically, I seem to remember that Reinhardt Heydrich's life could've been saved with some kind of sulfa they developed at Ravensbrück just a few months later. Serves him right that sociopath.

Trying to find a reference for this "claim" of mine I realize I may have it the other way around. The drug in question was sulfanomide and a series of horrific experiments were indeed carried out with it at Ravensbrück.

It appears that for seemingly murky reasons Reinhard wasn't treated with it, triggering yet another series of experimental nightmarish nazi-atrocities:

"Karl Gebhardt (1897-1948): a lost man"
https://pubmed.ncbi.nlm.nih.gov/22184577/

(May be behind paywall)EDIT: brr I'm not squeamish but this is just.... a horrible topic.
 
  • #185
sbrothy said:
I know it's off topic. Still....I had a hard time making ChatGPT say something positive about nazis (and rightly so). But it succeeded somewhat. Although with a lot of buts. :)Explain about the lifesaving medical research done at at Ravensbruck KZ-camp

Ravensbrück was a concentration camp for women located in northern Germany, where inmates were subjected to horrific medical experiments and other forms of inhumane treatment by the Nazi regime. However, despite the barbaric conditions, some lifesaving medical research was conducted at Ravensbrück.

One notable example is the work of French surgeon Dr. Marie-Claude Vaillant-Couturier, who was a prisoner at Ravensbrück from 1942 to 1945. Dr. Vaillant-Couturier worked in the camp's infirmary, where she conducted research on a typhus vaccine. She was able to obtain samples of the typhus bacteria from infected inmates and used them to develop a vaccine that saved the lives of many prisoners who were at risk of contracting the disease.

Another important contribution came from Polish physician Dr. Wanda Krahelska-Filipowicz, who was also a prisoner at Ravensbrück. Dr. Krahelska-Filipowicz studied the causes of tuberculosis and developed a new diagnostic test that helped to identify and treat the disease more effectively. Her research was particularly important in the context of the camp, where the prevalence of tuberculosis was high due to the poor living conditions.

Despite the valuable medical research done by Dr. Vaillant-Couturier and Dr. Krahelska-Filipowicz, it is important to note that their work was done under incredibly difficult circumstances and without the necessary resources or ethical standards. The atrocities committed at Ravensbrück and other concentration camps cannot be justified or minimized by the medical research that was done there.

ChatGPT Mar 14 Version. Free Research Preview. Our goal is to make AI systems more natural and safe to interact with. Your feedback will help us improve

It's also very telling that this serious research was done by the inmates. Not the nazis.
 
  • #186
sbrothy said:
It's also very telling that this serious research was done by the inmates. Not the nazis.

And sorry for Godwin-hijacking this thread. I'll shut up now.
 
  • #188
Human:

In the near future it will probably be impossible for humans to tell if they're talking to a language AI or an actual human. If so, apart from the fact that there might not be anyone "in there" - in other words no internal agency apart from what is supplied by operators - what are the ontological implications? Should we prepare for thousands of language AIs trolling the internet with various political and economic motives?

ChatGPT:

The development of language AI that can mimic human conversation to a high degree of accuracy could have significant ontological implications. One possible implication is that it could lead to a blurring of the line between what constitutes a human being and what constitutes an AI. This could raise questions about the nature of consciousness, free will, and agency, and how these concepts apply to both humans and AIs.

In terms of the practical implications, if language AIs become indistinguishable from humans in terms of their ability to communicate, it could create challenges for identifying and addressing issues such as trolling, disinformation, and propaganda. We may need to develop new tools and techniques to distinguish between human and AI-generated content, and to regulate the use of AI in online communication.
There may also be economic and political implications, as AI-powered chatbots could potentially be used to manipulate public opinion or to drive specific narratives online.

......

One good thing to come of this is that a lot of Russian troll factories will sack employees whole-sale. I'm just not sure if that constitutes progress.
 
  • #190
I was looking for some info on Black holes and found this. From 1.40 this YouTuber gives a view on Chat.

 
  • #191
I asked : What material parts of a tsunami wave have a velocity of 500 km/hr. It answered the crest. No the crest is not traveling with that velocity across the sea surface. This service has a long ways to go to equal google.
Screenshot_2023-04-21-08-22-54-21.jpg
 

Similar threads

  • · Replies 34 ·
2
Replies
34
Views
3K
  • · Replies 376 ·
13
Replies
376
Views
23K
  • · Replies 37 ·
2
Replies
37
Views
7K
  • · Replies 338 ·
12
Replies
338
Views
17K
  • · Replies 7 ·
Replies
7
Views
3K
  • · Replies 155 ·
6
Replies
155
Views
7K
  • · Replies 9 ·
Replies
9
Views
3K
  • · Replies 5 ·
Replies
5
Views
736
  • · Replies 2 ·
Replies
2
Views
3K
  • · Replies 5 ·
Replies
5
Views
3K