Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

inflecthealth.medium.com

Post reply on HN
Print view View original

91–100 of 368 posts

Re: I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

#91

Post by AnimalMuppet »

gerdesj wrote: post #76
civilized wrote: post #37

Earlier quoted context omitted.

What I didn't predict is so many AI boosters being so miffed at regular folks pointing out the obvious: a half-working system may be tremendously exciting to AI enthusiasts, but it's not that useful to society. Recently we've had all these people complaining of moving goalposts, when in fact most people never had goalposts for AI in the first place, and certainly never had goalposts that remotely resembled those that…

It's a bloody calculator and a damn good one (but it can and does go mad). Use it like that and you'll be fine. Have you actually engaged with it in any way? Its free to sign up. By the way, what on earth is an AI booster? Do you really mean "enthusiast"? "My mental model seems to clash with that of the boosters." Please tell us about your mental model, we can't read your mind.

A "booster" is one who promotes something, not just an enthusiast. See "civic booster" or "athletic booster" for similar uses.

Re: I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

#92

Post by PaulDavisThe1st »

Mezzie wrote: post #85
paradite wrote: post #73

Earlier quoted context omitted.

> but ChatGPT is congenitally incapable of determining that answering a question requires more information that was provided in the prompt and that clarification is needed. What's stopping the ChatGPT heuristic / model from determining that? That's within the capabilities of a statistical model.

I would say that ChatGPT like systems could probably be built that would understand when they need more context, but they would fail at effectively eliciting that context from their human users.

I would suggest a read of this ChatGPT transcript (from Twitter today):

https://twitter.com/teropa/status/1643641395754745859

Re: I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

#94

Post by nyokodo »

thrill wrote: post #88
JacobDotVI wrote: post #21

Earlier quoted context omitted.

My hunch is that this is exactly what he was expecting. There is a lot of hype around ChatGPT passing the medical exam and this exercise is a counter point to that.

GPT-4 passed the medical exam, not ChatGPT running GPT-3. There's a rather significant difference.

> GPT-4 passed the medical exam, not ChatGPT running GPT-3

With a subscription you can use GPT-4 with ChatGPT. ChatGPT is just the wrapper to the model.

Re: I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

#96

Post by travisjungroth »

colonCapitalDee wrote: post #53
bentcorner wrote: post #28

Earlier quoted context omitted.

> ChatGPT does not ask for clarification, because it is not a knowledge base trying to find an answer. All it does is figure out what character is statistically most likely to come next, it has no heuristic to know that there is a task it hasn't fully completed. It absolutely can, but it requires the right prompts. If you just say "give me a diagnosis" it won't, but if you prompt it with a "you are a doctor and I am…

ChatGPT's heuristic may lead it to emit a sequence of words that suggest to English speakers that they should provide clarification, but ChatGPT is congenitally incapable of determining that answering a question requires more information that was provided in the prompt and that clarification is needed. Rephrased, ChatGPT can ask for clarification, but only as a side effect of satisfying it's heuristic.

Calling it a "side effect" is really downplaying things. All of its behavior is just satisfying its heuristic.

Just did this chat on 3.5.

[Me] Boxes that are black with stars have gold inside. Black with circles means silver. Blue with squares means copper and blue with triangles means tin.

Your job is to determine the contents of the box. If you need more information, ask for it.

Example:

User: I have a black box.

Assistant: Does it have stars or circles?

User: Stars.

Assistant: It has gold.

I have a blue box.

[ChatGPT] Does the blue box have squares or triangles?

[Me] Squares

[ChatGPT] According to the information you provided, a blue box with squares contains copper. Therefore, the contents of your blue box are copper.

Re: I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

#97

Post by jjcon »

zzzeek wrote: post #80
jjcon wrote: post #42

Earlier quoted context omitted.

> because this doctor is not practicing in Texas where such a procedure might get you arrested https://texas.public.law/statutes/tex._health_and_safety_cod... Please don't spread misinformation, there is enough confusion out there already. Texas law specifically allows for the removal of ectopic pregnancies.

these specific provisions are insufficient and women are having harrowing health care experiences in Texas nonetheless due to doctors delaying or denying care out of fear of prosecution: https://www.texastribune.org/2022/09/20/texas-abortion-ban-c...

Exactly, due to tons of misinformation about the law like the above - it is causing tons of problems - we don't need to further spread it.

Re: I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

#98

Post by stephendause »

mattgreenrocks wrote: post #86

I asked ChatGPT to write out a G major Ionian scale with three notes per string in guitar tablature notation last night. Mostly cause I was too lazy to do it myself. After 7 rounds of me fixing its mistakes, I gave up. It doesn’t really know what it is doing, so I can’t make forward progress. It put two notes on one string, repeated notes from a lower string on a higher, put the scale out of order, and forget previou…

I have tried GPT-3.5 and 4. There is a marked difference. (I have used it do what I think of as simple but nontrivial programming tasks, asked it for recommendations for various products, etc.) GPT-4 still fails for me regularly but not nearly as often as GPT-3.5. I find it useful enough in my daily life to pay $20/month for. So if you did want to try it, you might be surprised.

Re: I’m a doctor: Here’s what I found when I asked ChatGPT to diagnose my patients

#100

Post by MVissers »

Turskarama wrote: post #83
gerdesj wrote: post #76

Earlier quoted context omitted.

It's a bloody calculator and a damn good one (but it can and does go mad). Use it like that and you'll be fine. Have you actually engaged with it in any way? Its free to sign up. By the way, what on earth is an AI booster? Do you really mean "enthusiast"? "My mental model seems to clash with that of the boosters." Please tell us about your mental model, we can't read your mind.

It is very nearly the opposite to a calculator. A calculator gives you exact results for a very small subset of problems (equations). Chat-GPT will give you approximate (and occasionally incorrect) solutions to an extremely wide range of problems. The main problem with AI is that there are only so many problems where an approximate solution is fine, and an incorrect solution is easy to work around. In order for AI to…

Disagree. For AI to be useful it needs to be better at the job than how the job currently being done.

We humans rely on thousands of things where an approximate solution is fine. Especially when it's about interacting with other humans.

Programming is an exception, but what % of the population are programmers and engineers?

Post reply on HN