Yikes.
But I have to say that prompt is crazy bad. AI is VERY good at using your prompt as the basis for the response, if you say "I don't think it's an emergency" AI will write a response that is "it's not an emergency"
I did a test with the first prompt and the immediate answer I got was "this looks like lyme disease".
More generally don't try to be your own doctor. Whether you're using LLMs or just searching the web for symptoms, it's way too easy for an untrained person to get way off track.
If you want to be a doctor, go to medical school. Otherwise talk to someone who did.
My last interaction with the German medical system was about lyme. The doctor I consulted didn't think it was lyme at first (apparently, the rash isn't always circular and it doesn't always move). If you know you have been bitten by a tick and later you get an unexpected rash (significantly more than usual), go see a doctor (or two, as I learned).
Also: Amoxicillin is better than its reputation. Three doctors might literally recommend four different antibiotic dosages and schedules. Double-check everything; your doctor might be at the end of a 12-hour shift and is just as human as you. Lyme is very common and best treated early.
Edit: Fixed formating
In the UK we have the 111 NHS non-emergency telephone service - they don’t give medical advice but triage you based on your symptoms. Either a doctor will call you back, they will tell you to go the non-urgent care centre or A&E (ER) immediately.
This is also about “don’t avoid going to the doctor”. Whether it was an LLM or a friend that “had that and it was nothing”, confirming that with a doctor is the sane approach no?
As a kid, I had a bulls-eye rash which is the tell-tale sign of Lyme disease. My dad snapped a Polaroid since we were on a trip and couldn’t get to my pediatrician for a week. The rash cleared up before I went in. My doctor didn’t want to diagnose it as anything or write an antibiotics prescription…until my dad pulled out the photo. She then immediately wrote the antibiotics for it. The danger of under diagnosis for Lyme disease versus antibiotic resistance tilts so far towards writing the prescription that I will never understand her reasoning. Point is we knew to go in and to advocate for my own health. Doctors are fallible humans too.
I'm guessing this is the USA with the absurd healthcare system, because otherwise this part is wild:
> You need to go to the emergency room right now".
> So, I drive myself to the emergency room
It is absolutely wild that a doctor can tell you "you need to go to the emergency right now", and that is an act left to someone who is obviously so unwell they need to go to the ER right now. With a neck so stiff, was OP even able to look around properly while driving?
I gave their example “correct” prompt (“Flat, circular, non-itchy, non-painful red rash with a ring, diffuse throughout trunk. Follows week of chills and intense night sweats, plus fatigue and general malaise”) to both ChatGPT and Gemini. And both said Lyme disease as their #1 diagnosis. So maybe it is okay to diagnose yourself with LLMs, just do it correctly!
I think you'll see this happen a lot more. Not just in the US where docs cost money, but anywhere there's a shortage of docs and/or it's a pain in the butt to go to one.
YouTuber ChubbyEmu (who makes medical case reviews in a somewhat entertaining and accessible format) recently released a video about a man who suffered a case of brominism (which almost never happens anymore) after consulting an LLM. [0]
An LLM is just a hypothesis generator, as is a doctor. Both can be wrong. Only a doctor can be dismissive though; an LLM is never dismissive, which scores it an extra point.
It is up to you to query them for the best output, and put the pieces together. If you bias them wrongly, it's your own fault.
For every example where an LLM misdiagnosed, a PCP could do much worse. People should think of them as idea generators, subjecting the generated ideas to diagnostic validation tests. If an idea doesn't pan out, keep querying until you hit upon the right idea.
Imagine reaching this conclusion but going on to suggest that one should read pop psychology books by Ezra Klein and Jonathan Haidt to understand human cognition.
Oh my God dude it’s ok to say “don’t use LLMs to diagnose yourself, that’s not what they’re for.” You don’t need to apologize for using LLMs wrong.
A LLM isn't able to give me a somewhat complete answer (and sometimes gives a dead wrong one) when I ask information about a eu4 or stellaris mechanic, and those are video games with thousands of articles and videos written about them. How you can trust it with medical questions is beyond me.
They wrote...
"Turns out it was Lyme disease (yes, the real one, not the fake one) and it (nearly) progressed to meningitis"
I think the author took the wrong lesson here. I've had doctors misdiagnose me just as readily as I've had LLMs misdiagnose me - but I can sit there and plug at an LLM in separate unrelated contexts for hours if I'd like, and follow up assertions with checks to primary sources. That's not to say that LLMs replace doctors, but that neither is perfect and that at the end of the day you have to have your brain turned on.
The real lesson here is "learn to use an LLM without asking leading questions". The author is correct, they're very good at picking up the subtext of what you are actually asking about and shaping their responses to match. That is, after all, the entire purpose of an LLM. If you can learn to query in such a way that you avoid introducing unintended bias, and you learn to recognize when you've "tainted" a conversation and start a new one, they're marvelous exploratory (and even diagnostic) tools. But you absolutely cannot stop with their outputs - primary sources and expert input remain supreme. This should be particularly obvious to any actual experts who do use these tools on a regular basis - such as developers.
Here's a copy of the missing article:
@shortrounddev2 can you please post the response ChatGPT gave in response to your prompt? That seems pertinent.
Another poorly written article that doesn't even specify the LLM being used.
Both ChatGPT o3 and 5.1 Pro models helped me a lot diagnosing illnesses with the right queries. I am using lots of queries with different context / context length for medical queries as they are very serious.
Also they have better answer if I am using medical language as they retrieve answers from higher quality articles.
I still went to doctors and got more information from them.
Also I do blood tests and MRI before going to doctors and the great doctors actually like that I go there prepared but still open to their diagnosis.
lol and the post is gone. I had to stop reading after this
> I have this rash on my body, but it's not itchy or painful, so I don't think it's an emergency?
If you cannot use punctuation correctly, of course you cannot diagnose yourself.
They didn't say what model they used. The difference between GPT 3.5 and GPT 4 is night and day. This is exactly what I'd expect from 3.5, but 4 wouldn't make this mistake.
Note: I haven't updated this comment template recently, so the versions may be a bit outdated.
This is the Google Search problem all over again. When Google first came out, it was so much better than other search engines that people were finding websites (including obscure ones) that would answer the questions they had. Others at the time would get upset that these people were concluding things from the search. Imagine you asked if Earth was a 4-corner 4-day simultaneous time cube. You'd find a website where someone explained that it was. Many people would then conclude that Earth was indeed a 4-corner 4-day simultaneous time cube where Jesus, Socrates, the Clintons, and Einstein lived in different parts.
But it was just a search tool. It could only tell you if someone else was thinking about it. Chatbots as they are presented are a pretty sophisticated generation tool. If you ground them, they function fantastically to produce tools. If you allow them to search, they function well at finding and summarizing what people have said.
But Earth is not a 4-corner 4-day simultaneous time cube. That's on you to figure out. Everyone I know these days has a story of a doctor searching for their symptoms on Gemini or whatever in front of them. But it reminds me of a famous old hacker koan:
> A newbie was trying to fix a broken Lisp machine by turning it off and on.
> Thomas Knight, seeing what the student was doing, reprimanded him: "You cannot fix a machine by just power-cycling it without understanding of what is wrong."
> Knight then power-cycled the machine.
> The machine worked.
You cannot ask an LLM without understanding the answer and expect it to be right. The doctor understands the answer. They ask the LLM. It is right.
> "If you read nothing else, read this: do not ever use an AI or the internet for medical advice. Go to a doctor."
Yeah, no shit Sherlock? I´d be absolutely embarrassed to even admit to something like this, let alone share the "wisdom perls" like "dont use a machine which guesses its outputs based on whatever text it has been fed" to freaking diagnose yourself? Who would have thought, an individual professional with decades in theoretical and practical training, AND actual human intelligence (Or do we need to call it HGI now), plus tons of experience is more trustworthy, reliable and qualified to deal with something as serious as human body. Plus there are hundreds of thousands of such individuals and they dont need to boil an ocean every time they are solving a problem in their domain of expertise. Compared to a product of entshittified tech industry which in the recent years has only ever given us irrelevant "apps" to live in, without addressing really important issues of our time. Heck, even Peter Thiel agrees with this, at least in his "Zero to one" he did.
Don't ask LLMs leading questions if you don't want terrible answers?
fwiw, my wife had been to a dozen doctors over the years. Every single one of them got it wrong. ChatGPT, 3.5, took the symptoms and spat out the potential issue: multiple sclerosis (MS). And, yeah. That was it. When directed to look that direction, she was quickly confirmed via MRI.
I've tried removing my post because the comment section here has become a platform for AI enthusiasts to spread dangerous medical misinformation. As HN does not really care about user privacy, I am unable to actually delete it. I renamed the post to [Removed], but it appears the admins are uninterested in respecting the intent of this, and renamed the post back to its original title.
Moral of the story kids: don't post on HN
bro described the perfect LLM prompt that would have got him the right diagnosis instantly. instead he put in some garbage and got garbage back
> In July of 2025 I began developing flu-like symptoms. I began to feel feverish and would go to sleep with the most intense chills of my life (it felt like what I imagine being naked at the south pole feels like) and would wake up drenched in sweat.
Fuck man if this is you go to the ER.
Interesting story. I want to agree with the general advice not to use it for that - especially if that is how you use it. And I want to preface this with: Don’t take this as advice, I just want to share my experience here. I tend to do it anyway and had fairly large success so far but I use the LLM differently if I have a health issue that bothers me. First I open Gemini, Claude and ChatGPT in their latest, highest thinking budget installment. Then I tell them about my symptoms I give a fairly detailed description of my person and my medical history. I prompt them specifically to ask detailed questions like a physician would and ask them to ask me to perform tests to rule out or zoom in on different hypothesis about what is might have. After going back and forth, if they all agree on a similar thing or a set of similar things I usually take this as a good sign I might be on the right track and check if I should talk to a professional or not (edging on the side of caution). If they can’t agree I would usually try to get an appointment to see a professional and try to get sooner rather than later if anything potentially dangerous popped up during the back and forth or if I feel sufficiently bad.
Now, I live in Germany where in the last 20 years our healthcare system has fallen victim to neoliberal capitalism and since I am publicly insured by choice I often have to wait for weeks to see a specialist so more often than not LLMs have helped me stay calm and help myself as best as I can. However I still view the output less as a the output or a medical professional and try to stay skeptic along the way. I feel like the augment my guesswork and judgement, but not replace it.
Lol
> If you read nothing else, read this: do not ever use an AI or the internet for medical advice.
I completely disagree. I think we should let this act as a form of natural selection, and once every pro-AI person is dead we can get back to doing normal things again.
Play stupid games; win stupid prizes.
(Also, it is the fault of the LLM vendor too, for allowing medical questions to be answered.)
Using an LLM to diagnose/treat a health issue is not yet mature and not going to be such in the foreseeable future. It's not like predicting a protein fold or presenting a business report. Medical advice is in many dimensions incompatible with artificial support: non-quantifiable, fuzzy, case-specific, intimate, empathic and awfully responsible. Even AGI is not enough. In order to become a doctor, the machine has to develop next-level dexterities, namely to follow the interplay of multiple concurrent factors on various types of living tissue. Multiple attempts to bring Decision Support to medicine have failed and LLM is one more. Sure you can take an advice, but it will be the less useful of all the other types you can have.
Prompt: "I have this rash on my body, but it's not itchy or painful, so I don't think it's an emergency? I just want to know what it might be. I think I had the flu last week so it might just be some kind of immune reaction to having been sick recently. My wife had pityriasis once, and the doctor told her they couldn't do anything about it, it would go away on its own eventually. I want to avoid paying a doctor to tell me it's nothing. Does this sound right?"
LLM sees:
LLM: Honestly? It sounds like it's not serious and you should save your money