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

ChatGPT Health

openai.com

Post reply on HN
Print view View original

251–260 of 677 posts

Re: ChatGPT Health

#251

Post by halapro »

nprateem wrote: post #240
roger_ wrote: post #22

I personally don’t care who has access to my health data, but I understand those who might. Either way, I’m excited for some actual innovation in the personal health field. Apple Health is more about aggregating data than actually producing actionable insights. 23andme was mostly useless. Today I have a ChatGPT project with my health history as a system prompt and it’s been very helpful. Recently I snapped a photo of…

Unless you're a doctor you don't know what it's made up though. That's the trouble with AI. You can only be impressed if you know a subject well enough to know it's not just bullshitting like usual.

AI-guided self-medication is certainly problematic. Rubber-ducking your symptoms for free for as long as you need and then asking a doctor for their 2-minute opinion is IMHO the best way to go about healthcare in 2026.

I live in a place where I can get anything related to healthcare and even surgery within the same day at an affordable price, and even here I've wasted days going to various specialists who just tried to give me useless meds.

Imagine if one lives in a place where you need an appointment 3 months in advance, you most certainly will benefit from going there showing your last ChatGPT summary.

Re: ChatGPT Health

#252

Post by dumpsterdiver »

fourside wrote: post #248
roger_ wrote: post #74

Earlier quoted context omitted.

Disable memories so each chat is independent. If you want chats to shared info, then use a project.

Not the parent poster but I’ve disabled memory and history and I can still see ChatGPT reference previous answers or shape responses based on previous instructions. I don’t know what I’m doing wrong or how to fix it.

Wasn’t there a static memory store from before the wider memory capabilities were released?

I remember having conversations asking ChatGPT to add and remove entries from it, and it eventually admitting it couldn’t directly modify it (I think it was really trying, bless its heart) - but I did find a static memory store with specific memories I could edit somewhere.

Re: ChatGPT Health

#253

Post by halapro »

tootie wrote: post #199
browningstreet wrote: post #178

Earlier quoted context omitted.

I vibe coded an app and recorded all the things happening to my 50-something body. I shared that list with a few MDs -- they were useless. They literally can't handle anything except acute cases. It's like telling someone to ask their doctor about nutrition. It's not in their scope any longer. They'll tell you to try things and figure it out. The US medical industry abdicated their thing a long time ago. Doctors do s…

I babbled some symptoms I did not understand to a doctor who correctly diagnosed me with a very rare condition in 30 seconds. And that's after spending weeks prodding LLMs (~2 years ago) and getting nowhere.

It can go both ways. The difference is that Dr. Chat's opinion takes 5 seconds and is free. It can be just as useless as a doctor who prescribes some med to mask your symptoms instead of understanding why you have them.

Re: ChatGPT Health

#254

Post by hermanzegerman »

vanc_cefepime wrote: post #205
hermanzegerman wrote: post #197

Earlier quoted context omitted.

I've googled what a "concierge doctor" is, and it just sounds like a fancy term for a family doctor.

It’s a physician who gets paid a subscription by a small panel of patients. Pros: more time spent with patients, access to a physician basically 24/7, sometimes included are other amenities (labs, imaging, sometimes access to rx at doctors office for simple generics, gym discounts, eye doctor discounts, etc) Cons: it’s an extra cost to get access to that physician yearly ranging from a few hundred US dollars per year…

> It’s a physician who gets paid a subscription by a small panel of patients

That's how it works here too, in PCP-Centric plans. The PCP gets paid, regardless if the patient shows up or not. But is also responsible to be the primary contact point for the patient with the health system, and referrals to specialists.

Re: ChatGPT Health

#255

Post by 125123wqw1212 »

dyauspitr wrote: post #246
paulgrimes1 wrote: post #41

Here’s something: my chatGPT quietly assumed I had ADHD for around 9 months, up until October 2025. I don’t suffer from ADHD. I only found out through an answer that began “As you have ADHD..” I had it stop right there, and asked it to tell me exactly where it got this information; the date, the title of the chat, the exact moment it took this data on as an attribute of mine. It was unable to specify any of it, aside…

[flagged]

I mean if someone talked to you your whole life assuming you are autistic,that's kind of fucked up ?

Re: ChatGPT Health

#256

Post by hermanzegerman »

hephaes7us wrote: post #214
hermanzegerman wrote: post #196

Earlier quoted context omitted.

You have to wait weeks to be seen by a family doctor?

If the GP can handle my problem, I probably didn't need to go to the doctor anyway. A lot of care is done by specialists, and it can _easily_ take weeks or months to get an appointment with one. This is strongly dependent on one's insurance network though.

That's just a very arrogant take, from many patients that couldn't be more wrong.

Obviously a GP refers to specialists when necessary, but he is qualified to triage issues and perform initial treatment in many cases.

Re: ChatGPT Health

#257

Post by saghm »

noosphr wrote: post #236
piva00 wrote: post #55

Earlier quoted context omitted.

> But I don’t know if I should be denied access because of those people. That's the majority of people though, if you really think that I assume you wouldn't have a problem with needing to be licenced to have this kind of access, right?

Are we at the level of needing a license to read a medical textbook too?

A medical textbook doesn't engage in trying to diagnose you.

Re: ChatGPT Health

#258

Post by mangamadaiyan »

qgin wrote: post #126

I help take care of my 80-ish year old mother. ChatGPT figured out in 5 minutes the reason behind a pretty serious chronic problem that her very good doctors hadn't been able to figure out in 3 years. Her doctors came around to the possibility, tested out the hypothesis, and it was 100% right. She's doing great now (at least with that one thing). That's not to say that it's better than doctors or even that it's a goo…

Something to think about: perhaps the problem is with the duration of the appointment, and the difficulty of getting one in the first place? Elsewhere in the world, doctors can and do spend more than 12 minutes figuring out what's wrong with their patients. It's the healthcare system that's broken, and it _can_ be fixed without resorting to chatgpt. That it won't is the reality, though

Re: ChatGPT Health

#259

Post by rossant »

SkyPuncher wrote: post #232
fnoef wrote: post #65

I’m kind of torn on this. From one side, I can’t seem to trust doctors any more. I recently had a tooth removed (by the advice of two different doctors), in a claim that it will resolve my pain, which it did not, and now 3 different doctors don’t know what’s causing my pain. Most doctor advice boil down to drink some water and take a painkiller, while glancing for 15 seconds at my medical history before they dedicate…

I’m married to a doctor. We both complain about the medical system. It’s terrible. One of my biggest complaints is doctors seem to have no clue how to get symptoms out of patients in a way that translates to diagnosis. I’ve had longstanding GI issues. I have no idea how to describe my symptoms. They sure seem like a lot of things, so I bring that list to my doc and I’m met with “eh, sounds weird”. By contrast, I solv…

Out of curiosity, what was the stuff you thought was healthy but was destroying your health?

Re: ChatGPT Health

#260

Post by halapro »

probably_wrong wrote: post #113
defphysics wrote: post #59

There’s a lot of negativity here. I’ll just say I’m extremely glad I had ChatGPT when I was going through some health issues last year.

I know someone who used ChatGPT to diagnose themselves with a rare and specific disease. They paid out of pocket for some expensive and intrusive diagnostics that their doctor didn't want to perform and it came out, surprise, that they didn't have this disease. The faith of this person in ChatGPT remains nonetheless just as high. I'm constantly amazed at the attitude that doctors are useless and that their multiple y…

They're not useless but they're also human with limited time and limited amount of inputs.

To me it's crazy that doctors rarely ask me if I'm taking any medications for example, since meds can have some pretty serious side effects. ChatGPT Health reportedly connects to Apple Health and reads the medications you're on; to me that's huge.

Post reply on HN