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

111–120 of 368 posts

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

#111

Post by vl »

jcims wrote: post #48

I know everyone scoffs at the concept of 'prompt engineer', but it really is an essential craft that we're going to have to come to terms with when interacting with large language models. Seeking suggestions on a more comprehensive prompt: https://sharegpt.com/c/sckAPvV Trying it out: https://sharegpt.com/c/LbpEIxi

I think there will be no such profession because both people and models will adapt to better understand each other.

This has already happened with Google - search got better over the years, but also people became better at doing good search queries!

Before there were typists, now everyone is a typist! And so on, historically information entry/retrieval jobs are eliminated and are moved to users.

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

#112

Post by dragonwriter »

vl wrote: post #111
jcims wrote: post #48

I know everyone scoffs at the concept of 'prompt engineer', but it really is an essential craft that we're going to have to come to terms with when interacting with large language models. Seeking suggestions on a more comprehensive prompt: https://sharegpt.com/c/sckAPvV Trying it out: https://sharegpt.com/c/LbpEIxi

I think there will be no such profession because both people and models will adapt to better understand each other. This has already happened with Google - search got better over the years, but also people became better at doing good search queries! Before there were typists, now everyone is a typist! And so on, historically information entry/retrieval jobs are eliminated and are moved to users.

> I think there will be no such profession because both people and models will adapt to better understand each other.

People have been working to understand each other better for as long as there have been humans, and yet we have humans whose work is specialized in providing direction, instruction, evaluation, and feedback to other humans.

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

#113

Post by ryanwaggoner »

MilStdJunkie wrote: post #109
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.

"Booster" can also now mean technologists who have correctly predicted the number and size of executive erections once teased with the idea of automating most of their office. Put on something black and tight, go up on stage and twirl around that notion until balled-up Jacksons grease the creaking floorboards. You know you'll be riding in a Cayenne tonight. Maybe a Boxster. It actually sounds pretty familiar for thos…

Upvoted for being the kind of comment AI can’t yet write.

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

#114

Post by TheRealPomax »

flir wrote: post #46

This is how I played doctor with ChatGPT. > Do you know what an Expert System is? [describes expert system] > I'd like you to emulate an expert system while I play the role of a patient. Expert systems ask questions in order to produce a diagnosis. I would like you to ask me a series of questions, and respond with a diagnosis when you feel confident. Alright, I'll do my best to emulate an expert system. Please keep i…

And failing at it, if you had to help it at every step.

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

#115

Post by AH4oFVbPT4f8 »

gilbetron wrote: post #24

Being a scifi geek and AI geek and neuroscience geek for pretty much the past 40 years, I've read countless predictions and scenarios and stories about society's response as "true" AI begins to emerge. So watching it play out for real is creating this bizarre sense of deja vu combined with fascination and frustration and also some anxiety. This article and the comments in this thread are right up that alley. I mean,…

I have case that 5 doctors so far can't explain. I fed in what was happening (generally speaking) and it provided a rather good list of what it "might" be. I then asked it to start describing each scenario and I was able to determine nope, that's not it or if it was plausible. Meeting with doctor no 6 tomorrow to talk about what it could be but at least I have a better insight at what the more obvious possibilities.

Side note, my ER doctor wrote me a referral to neurologist to who was considered the best in the state and they refused to even talk to me since the referral said car accident. They wouldn't budge and wouldn't reconsider. The car accident was a result of an episode, not the cause of my issues. I hate the US healthcare system.

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

#116

Post by Genbox »

gilbetron wrote: post #24

Being a scifi geek and AI geek and neuroscience geek for pretty much the past 40 years, I've read countless predictions and scenarios and stories about society's response as "true" AI begins to emerge. So watching it play out for real is creating this bizarre sense of deja vu combined with fascination and frustration and also some anxiety. This article and the comments in this thread are right up that alley. I mean,…

I've noticed a very weird trend when trying to incorporate GPT4 into my workflow. I lead a small team of developers and security consultants, and whenever someone runs into a problem, it is immediately searched for on the web. However, there is a real resistance/reluctance in using GPT for the same task.

I think it is a combination of factors. The wrong answers are part of it, but I think another part is the anthropomorphization of it makes it almost like asking another human for help, which is somehow 'less good' than asking a search engine.

For better or worse, LLMs are here to stay.

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

#117

Post by bsuvc »

debacle wrote: post #44

Devil's advocate, but maybe this doctor should be better at charting?

This is what I was thinking too.

Often when I find a response to be lacking, I try again with a better prompt and get the kind of response I was looking for.

Part of AI's effectiveness is in the human's ability to prompt well.

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

#118

Post by lamontcg »

I'm finding more or less the same behavior with ChatGPT when it comes to programming problems. If I feed it some leetcoding-like problem it usually gets a pretty good answer. I used it to write some rust code to strip-underline-followed-by-trailing-digits off a string. The first guess it made though was to strip a substring, and it missed the fact that the slice it was using could panic. The third try at least passed my "peer review".

It was useful because after a decade of using ruby my instinct is to reach for regexp captures, the solution it came up with is probably a lot faster and easier to read and avoids "now you have two problems".

I tried to get it to help me eliminate an allocation caused by the capture of variables in a lambda expression in C# and it just started to aggressively gaslight me and break the code and claim it was fixed (very assertively).

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

#119

Post by 627467 »

I wonder if you could prompt engineer your way to chatGPT to pretend to be a doctor and behave like one in, like, asking questions.

Many already said, chatGPT is not optimized for any scenario. I don't doubt that training it for medical applications is already underway. I mean, flesh and bone doctors in many countries already behave as bots essentially reading/answering through a sequence of questions on a screen. I can definitely see most GP being replaced by bots of sometime or people who are actually trained to display empathy with patients.

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

#120

Post by dougmwne »

civilized wrote: post #37
gilbetron wrote: post #24

Being a scifi geek and AI geek and neuroscience geek for pretty much the past 40 years, I've read countless predictions and scenarios and stories about society's response as "true" AI begins to emerge. So watching it play out for real is creating this bizarre sense of deja vu combined with fascination and frustration and also some anxiety. This article and the comments in this thread are right up that alley. I mean,…

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…

This is the self driving car argument applied to things it doesn’t fit. Sure, unless a self driving car is several 9’s reliable, it’s not terribly useful for society. That’s because there’s no way for a human to be safely in the loop at highway speed.

But a LLM assisting a wide rage of professionals at even a low accuracy could be part of an efficient workflow, allowing for be doctor or lawyer to give quality service to more people.

Post reply on HN