With the healthcare prices increasing at the breakneck speed, I am sure AI will take more and more role in diagnosing and treating people's common illnesses, and hopefully (doubt it), the some of that savings will be transferred to the patients.
P.S. In contrast to the US system, in my home city (Rangoon, Burma/Myanmar), I have multiple clinics near my home and a couple of pharmacy within two bus stops distance. I can either go buy most of the medications I need from the pharmacy (without prescription) and take them on my own (why am I not allowed to take that risk?) OR I can go see a doctor at one of these clinics to confirm my diagnosis, pay him/her $10-$20 for the visit, and then head down to the pharmacy to buy the medication. Of course, some of the medications that include opioids will only be sold to me with the doctor's prescription, but a good number of other meds are available as long as I can afford them.
The trouble is you are not educated enough to tell what is simple and what isn't. A cough could be a cough or it could be something more serious, only a "real" examination will reveal that. And sometimes even that's not enough, you need an examination by a specialists.
I'll tell you a story. Once upon a time I got pain in my balls. I went to a doctor and he felt around and he said he didn't feel anything. I went to another doctor and he felt something, but he had no idea what it was. He said could be a cyst, could be a swollen vein, could be an infection - he didn't even know if it was on the testicle or on the tube thingy.
Then I went to a Urologist. You can tell this man has felt up a lot of balls. He felt me up and said, "yup, that's a tumor" almost immediately. He was right, of course, and he ended up being the one to remove it too. Since I caught the cancer pretty early the chemotherapy wasn't too intense.
Point is, expertise matters when things aren't straight forward. Then, experience and perspective gets to shine.
[0] https://www.mayoclinic.org/diseases-conditions/henoch-schonl...
And even there, I bet ChatGPT would have told you to go see a doctor, since it can't feel your balls. And after your first appointment, if you had told it that you still thought something was wrong, it would probably have told you to go see a urologist.
So what is the value add of ChatGPT in this scenario? Either it says you don't need to see the doctor which could very well kill you or it tells you to visit the doctor and it doesn't actually help you in any way.
So, a technical solution to a bureaucratic problem.
Also, even when I'm on a PPO plan instead of HMO...I know when I have a yeast infection. I don't want to pay $100 to tell a doctor that I have a yeast infection. They don't even look at my genitals - they just take my word for it. But I can't buy fluconazole without a prescription. Such a waste of everyone's time and my money.
So again, a technical solution to a bureaucratic problem.
The AI is just making an already convoluted system more convoluted.
(If your HMO charges $200 for a PCP visit - wow, I’d look for a different plan.)
Mistakes will happen, that's the nature of statistics of this nature. But don't forget that saving 1,000s of people time is worth something, even if you never directly see it like you do the one case that it didn't catch.
How many unnecessary deaths does that buy you?
Which invalidates the whole point. There are countless ways that the healthcare industry could save time if it was willing to sacrifice an unknown number of lives.
How is this scenario any different from some other arbitrary decision made for the sake of expediency such as doctors deciding to no longer collect medical histories from new patients? Think of all the time that could be saved if you never had to fill out those forms the first time you saw a doctor. Who cares if that leads to more people dying, it saves some time!
You're saying "some change is bad therefore all changes are bad", which is obviously fallacious.
I did not advocate for this specific release being better, and I certainly did not say we should "move fast and break things". I don't know who you think you're arguing against but it's not me.
I only pushed back on the specific idea that this there is no possible value-add by this kind of software.
Not _yet_!
The third doctor used to behave more like the first two. In a world where ChatGPT replaced the rookies, how do we get good doctors?
And, for the record, I was referred to a Urologist. The doctor was able to say "something isn't right but I don't know what" and he referred me to a Urologist and got my ultrasounds.
No offense to uh... AI... but it's not very good at being humble. It seems hubris wasn't in the training data. It's quite difficult to get an LLM to say "I don't know". Usually you have to prime it or ask leading questions, which at that point you already know that it doesn't know so therefore trying to elicit that response is worthless.
Because you're paying for the expertise of someone who studied for more than a decade which you won't get from a random web search.
An AI system with today's technology should be less trustworthy for medical diagnosis than a web search. At least with a web search you might stumble upon a site with content from experts, assuming you trust yourself to be able to discern expert advice from bot-generated and spam content. Even if a doctor is doing the searching instead of me, I would pay them only for their knowledge to make that discernment for me. Why you think an AI could do better than a human at that is beyond me.
Your question reminds me of that famous Henry Ford GE invoice story:
> Making chalk mark on generator: $1.
> Knowing where to make mark: $9,999.
> Why you think an AI could do better than a human at that is beyond me.
You strike me as someone who thinks like me before I started using LLMs. Now when I read things like this rather than thinking in terms of black and white like I might have before, I instead think about percent likelihoods, and once you let in the grey it's no longer a matter of can/cannot but how many resources will be invested into making it so.
I think you hold doctors in pretty high esteem and I'm not sure how many other people hold doctors in as high esteem as you do. I've certainly ended up worse for having visited one. How seriously do you think most doctors take continuing education, particularly if they are overworked? An AI can consume the latest research/guidelines/text books immediately. Doctors can often act on 20 year old medical dogma. AI can get immediate social media feedback weighted in a way professionals deem appropriate.
I think diagnostic work is one of the things most likely to be taken over by AI. Even when asking specific technical questions in my own field, AI is capable of hitting some key points, and with extra prodding even getting to some very very specific niche points without too much coddling.
Cool, except I've been using LLMs since their inception, and they're now part of my daily workflow, for better or worse. My opinion is based purely on my experience as a user over the last few years.
Besides, my point in that paragraph was specifically about the ability to judge accuracy in information and to produce accurate information, not whether AI can outperform humans in other tasks. Modern AI systems fail miserably at this, which might be acceptable for casual use, but when human lives depend on that accuracy, such as in the healthcare industry, the process of integrating them should be gradual, with a lot of oversight and regulation. We've done that in the automotive industry, for obvious reasons, and the same should be done in others.
> I think you hold doctors in pretty high esteem and I'm not sure how many other people hold doctors in as high esteem as you do.
We hold the medical profession, not individual doctors, in high esteem for good reasons. It is critical to society, and requires intense education for many years. At the end of the day, doctors are as fallible as any human, but they're required to be licensed, and we have regulations in place for medical malpractice. The idea that a computer system based on probabilities and randomness, that hallucinates most of the time, will be more reliable than the average human doctor is ludicrous, regardless of what some benchmark says.
I'm not against using AI in healthcare. Pattern matching to detect early stages of cancer is a very good use case that's been helping radiologists for many years now. But that's the key word: _helping_. My concern is that when these systems are used for medical diagnosis and advice, they will instead be relied on much more than they should be.
This is the problem with reasoning from first principles. This statement is easily proven false by giving it a try, whether it "should" be true or not.
AI can take your entire medical history and the entire history of physics, chemistry, biology, and medicine up to May 2025...
A human was sleep deprived in Med school 15 years ago.
> Why you think an AI could do better than a human at that is beyond me.
Why do you think an AI couldn't do better than a human, when we have ample evidence of computers/AI exceeding humans in many areas?
I was specifically referring to the ability of discerning between accurate content and nonsense. SOTA LLMs today produce nonsensical output themselves, partly due to their training data being from poor quality sources. Cleaning up and validating training data for accuracy is an unsolved and perhaps unsolvable problem. We can't expect AI to do this for us, since this requires judgment from expert humans. And for specific applications such as healthcare, accuracy is not something you can ignore by placing a disclaimer.
The main thing missing right now, imo, is the ability for LLMs to verify data via experimentation, but this is completely solvable.
Wikipedia says "Overdose of only a small number of capsules can be fatal" but the study they quote shows that you'd need to take 10x-20x the usual dose for the smallest amount that's been shown to kill anyone -- which is admittedly more narrow of a safety window than over-the-counter Tylenol/Acetaminophen/Paracetamol but still, few people take 10-20 pills in one day of something that says "take 1 per day".
We have a massive, massive shortage of doctors.
The industry is doing everything they can to make it worse by the day, so I won't hold my breath that we'll get the slightest bit of respite.
It'd obviously be ideal if everyone could see a doctor for an affordable price any time they wanted.
We don't live in the ideal world.
This would be a HUGE win for most people.
https://capa-acam.ca/pa-profession/pa-facts
https://www.srh-university.de/de/folder/news/2025/04-25/erst...
https://www.bigregister.nl/over-het-big-register/cijfers/ver...
In Germany and all other countries, PAs are unable to treat patients without direct oversight and they are single digit percentages compared to NPs.
It's clear you have no experience in this area, so I wonder why the need to comment at all?
The data clearly shows that PA numbers continue increasing in many countries, so obviously they don't consider it a failed experiment and you're just lying to push some kind of personal agenda. It's clear you have no experience in this area, so I wonder why the need to comment at all?
Unfortunately medicine at the high level always has to cater to the lowest common denominator.
Personally, while I agree AI can probably take up some of the mundane triage I have some reservations about AI in its current LLM form being a good judge as patients are unreliable narrators and doctors rely on many senses and heuristics to make their recommendations.
An AI fine tuned to be a doctor with perfect health data and patient history is an interesting prospect, especially given the loss of the "family doctor" but that kind of data collection is a way away and has other Pandora's box considerations
Antibiotics must only be prescribed against bacterial type infections, and that is indeed one of the reasons a physician's consult is required, so that the physician can discern whether it's viral or bacterial, and choose an appropriate course of action. Malpractice indeed for making such a rookie mistake.
Pneumonia, being frequently caused by bacteria, is definitely something they'll prescribe antibiotics for, so a positive diagnosis would be a key first step there.
So it is quite telling, isn't it, that many people believe that taking antibiotics can cure viral infections, because if they were OTC they could really get abused in that respect, couldn't they!
This insanity needs to be regulated yesterday.
Because while LLMs obviously have massive limitations, so do humans, and it's not entirely clear to me that some synthesis of the two can't produce much better results than either on its own.
In theory, I agree with you. The world "some" is doing a lot of heavy lifting there though. I only hope that whatever definition of some emerges, it's not a horribly flawed one.
We see this today with AI-generated content on the web, and a flood of sloppily put together software produced by people who swear that AI is making them more productive. There's little interest in judging the output, and a lot of interest in lazy cash grabs. There are no guardrails in place in the healthcare industry AFAIA to prevent the same happening there, which is a scary thought.
The best we can do is test a human's mastery of a subject to estimate how well they actually know and understand that topic. Which is exactly what OpenAI is doing here.
What I care about is the results. If the "grade" is 10%, then I don't want to rely on it, whether it's a human or an AI. If it's 95%, then I feel fine about relying on it. Especially since I suspect that very soon, most doctors would not score as well on a benchmark like this as the SOTA models.
So you judge mastery of a subject by some arbitrary grade? Produced, incidentally, by the same company that trained the model. But I'm sure they wouldn't cheat...
I also care about the results, but I judge it based on direct experience. IME the current SOTA models can't be relied on to accurately produce working code most of the time, yet I'm expected to trust they can produce accurate healthcare diagnosis and advice? Give me a break.
AI companies have sold us a fantasy that a neat computer trick, which can still be very useful for society, will somehow lead to AGI. Now that we're a decade into this hype cycle and investors are getting antsy, they're doubling down by anthropomorphizing the technology and selling us "chain of thought" and "reasoning", as if making everyone say these things will somehow magically produce intelligence.
What's really irresponsible is that the public and governments are buying into it, which is pushing the tech into industries that can actually harm people. Safety is not just about trusting some arbitrary grade.
The Transformer, nevermind GPT-3 did not exist a decade ago. I guess LLMs aren't the only things that hallucinate and spout confident nonsense.
>I also care about the results, but I judge it based on direct experience. IME the current SOTA models can't be relied on to accurately produce working code most of the time, yet I'm expected to trust they can produce accurate healthcare diagnosis and advice? Give me a break.
You don't see the fallacy of forcing your experience in one domain onto a completely unrelated one regardless of any evidence to the contrary (even if you don't trust open ai, this is hardly the only paper trialing SOTA LLMS for diagnosis)? What does code have to do with diagnosis ? And while the current SOTA is by no means perfect, if you can't get them to produce working code, that's a you problem. At the very least, many users would disagree.
Yeah benchmarks aren't perfect. Doesn't mean they aren't useful. Certainly a lot more useful than your approach.
I'm attributing the start of the current AI hype cycle to the resurgence of CNNs using GPUs, roughly around the time of AlexNet and AlphaGo, not to LLMs and the Transformer architecture. Though if we're being really pedantic, the original Transformer paper is from 2017, so almost a decade ago. But this is beside my point.
> You don't see the fallacy of forcing your experience in one domain onto a completely unrelated one
The machine has no concept of a "domain". Whether it's outputting code, poetry, images, or video, it's all data generated by probabilistic pattern matching and pseudo-randomness. The structure and accuracy of the generated data is meaningful only to humans, and it's the most important factor that is measured in all these benchmarks.
We might find it collectively amusing when an AI produces funny text and weird looking pictures and video. Some might find it acceptable when it produces buggy code that humans need to fix, or when it mimics an expert by confidently spouting nonsense, which is where I personally draw the line. But we should all be concerned when the same models are used in industries where human lives depend on critical thinking by experts.
We have been promised fully autonomous vehicles for more than a decade now, and only in the last couple of years have some parts of that promise begun to come true in very limited scenarios. We're all understandably reluctant to give control of a speeding 2-ton object to a machine, for obvious reasons. The process has been very gradual, with a lot of oversight and regulation, as there should be. All I'm saying is that there should be an equal amount of oversight in other industries as well, particularly healthcare. Arbitrary benchmarks don't make me trust these systems more, regardless of who produces them.
The current hype cycle, the one fueling hundreds of billions in investment by multiple of the biggest tech companies in the world has little to do with Alex Net and AlphaGo and everything to do with LLMs and generative AI in general.
>Though if we're being really pedantic, the original Transformer paper is from 2017, so almost a decade ago. But this is beside my point.
The transformer paper did not start the generative AI craze. GPT-3 in 2020 did it for the research world, and the release of ChatGPT in Nov 22 did it for the general public.
>The machine has no concept of a "domain". Whether it's outputting code, poetry, images, or video, it's all data generated by probabilistic pattern matching and pseudo-randomness. The structure and accuracy of the generated data is meaningful only to humans, and it's the most important factor that is measured in all these benchmarks.
What are you on about? Of course it does. This conversations are getting tiring. Yes, LLMs model concepts directly independent of the text it is trained on. This has been demonstrated multiple times including very recently again by anthropic. There is nothing random about the predictions they make.
And even if the machine didn't model these things directly, the concept of domains would still be relevant to the humans testing it as 'data' is not equal.
SOTA LLMs are good for diagnosis. That was evident even before this benchmark. I'm not talking about some imagined future. I'm talking about right now. Sticking your head in the sand because of your 'experience' with coding is nonsensical. The benchmarks aren't arbitrary - In some cases they are directly testing the ability in question.
I'm not advocating for removing doctors from the picture entirely. It wouldn't even be possible even if I was, at least at the moment.
My experience is the opposite.
[1] https://psnet.ahrq.gov/primer/duty-hours-and-patient-safety
[2] https://www.fmcsa.dot.gov/sites/fmcsa.dot.gov/files/docs/Dri...
They were also found not to improve patient outcomes (possibly due to increased number of handoffs, which are highly error prone).
Turning the question around, if mandating shorter hours for physicians were found to result in higher rates of significant patient harm, would you be in favor of those restrictions?
less people using them.
I think the actually-relevant issue here is that until last month there wasn't API access for Grok 3, so no one could test or benchmark it, and you couldn't integrate it into tools that you might want to use it with. They only allowed Grok 2 in their API, and Grok 2 was a pretty bad model.
Also, only one out of the ten models benchmarked have open weights, so I'm not sure what GP is arguing for.
not talking about TFA or benchmarks but the news coverage/user sentiment ...
Gemini frequently avoids discussing health problems, which likely hurt its scores. My guess is any censorship was considered a fail.
Finally I typed in my entire history into o3-deep-research and let it rip for a while. It came back with a theory for the injury that matched that one doctor, diagrams of muscle groups and even illustrations of proposed exercises. I'm not out of the woods yet, but I am cautiously optimistic for the first time in a long time.
No doctor or physio has ever been able to fix my chronic issues, and I've always had to figure them out myself through lots of self-study and experimentation.
Yes, they propose exercises.
No, they don't work.
For certain (common) conditions, PT seems to have it nailed - the exercises really help. For the others, it's just snake oil. Not backed by much research. The current state of the art is just not good when it comes to chronic pain.
So while I don't know if an LLM can be better than a battery of human experts, I do know that those human experts do not perform well. I'm guessing with the OP's case, that battery of human experts does not lead to a consensus - you just end up with 10 different treatments/diagnoses (and occasionally, one is a lot more common than the other, but it's still wrong).
I would not expect most physicians to have a deep fund of literature-backed knowledge to draw from regarding exercise. Telling someone to do an exercise probably doesn't compensate well.
That said, I'm also pretty negative about the availability of rigorous literature regarding much of nutrition, dentistry, podiatry, physical therapy, etc... you know, the things that affect the health of most human beings that have ever lived.
Because there is so much variability in individual injuries and physiology it's extremely difficult to do rigorous studies comparing different treatments. Like even something common like a rotator cuff tear isn't one single thing that can always be treated the same way. Patients and practitioners will often have to follow a trial-and-error process until they figure out what works in a particular case. Experienced providers who see a lot of cases eventually develop a lot of tacit knowledge about this in a way that's difficult to codify or explain.
> Because there is so much variability in individual injuries and physiology it's extremely difficult to do rigorous studies comparing different treatments.
This is generally true of research in all areas of medicine; I don't see it as a fundamental reason why we wouldn't hope for equally powered and rigorous studies focusing on the issues that affect most of the population, even if there are not pharmaceutical or device companies that will profit from the recommended interventions.
I'm only a decade in, but my clinical experiences in my area of expertise vary widely from those of my colleagues, which vary from those of other colleagues, in spite of years of shared experience in a fairly homogenous demographic. Expert opinion is not a level of evidence that carries much weight in my mind.
It may be the best we have in many cases, I just wish we had something better.
Some specialist physicians have a deep knowledge of exercise for injury prevention and rehab. But it also helps to get input from a good physical therapist and/or personal trainer. As a patient it can be tough to discriminate the good ones from the quacks.
The endpoints for such research don't have to be problematic; regarding musculoskeletal complaints it's fairly straightforward to measure self-reported pain, self-reported level of function, or more objective measures like working days lost, strength, stamina, range of motion. The more difficult issue is determining an appropriate control group / placebo intervention.
(Also, I'll point out that my initial comment also included nutrition, dentistry, and several other fields under the same umbrella of "not enough good research" -- or to further specify, my complaint is that the burden of disease is disproportionate to the availability of rigorous literature.)
> Some specialist physicians have a deep knowledge of exercise for injury prevention and rehab.
By what measure? As in "they have a lot of clinical experience" -- (the "plural of anecdote")? Or as in they have read a lot of books on the subject? In which case, you seem to be agreeing that the evidence base is weak, so I'm not sure how authoritative this body of literature could be.
> As a patient it can be tough to discriminate the good ones from the quacks.
I imagine they would be virtually indistinguishable as a patient. Based on the context of this conversation, how would you recommend that I, as a physician, tell them apart? (It's hard enough to do with other physicians.)
Start with a dedicated orthopaedic practice who will make referrals to the above and then order CATs/MRIs if the above isn’t helping and evaluate if surgery is necessary.
One challenge is that it is hard to even know how to navigate all this. LLMs could actually help with that.
In general a lot of those injuries will eventually heal on their own. So it's easy to fool yourself into believing that a particular treatment was effective even when the real cure was time.
I think you should take a step back and re-assess your internal heuristics.
I've found o3 & deep research to be very effective in guiding my health plan. One interesting anecdote - I got hit in the chest (right over the heart) quite hard a month or so ago. I prompted o3 with my ensuing symptoms and heart rate / oxygenation data from my Apple watch, and it already knew my health history from previous conversations. It gave very good advice and properly diagnosed me with a costochondral sprain. It gave me a timeline to expect (which ended up being 100% accurate) and treatments / ointments to help.
IMO - it's a good idea to have a detailed prompt ready to go with your health history, height/weight, medications and supplements, etc. if anything's happening to you you've got it handy to give to o3 to help in a diagnosis.
After answering questions about symptoms, it gave me a few movements/actions to do and to rate the pain of each. Based on that it diagnosed me and gave me a timeline of what to expect and things to watch out for.
Really it was as helpful as a doctor could have been in that scenario, IMO.
So what use case does this test setup reflect? Is there a relevant commercial use case here?
For general medical Q&A I can't see how a specialized system would be better than base o3 with web search and a good prompt. If anything RAG and guardrail prompts would degrade performance.
It hallucinated serious cancer, along with all the associated details you’d normally find on a lab report. It had an answer to every question I had pre-asked about the report.
The report said the opposite: no cancer detected.
4o, o4? I'm certain it wasn't 3.5
Edit: while logged in
Sigh. This is a point in favor of not allowing free access to ChatGPT at all given that people are getting mad at GPT-4o-mini which is complete garbage for anything remotely complex... and garbage for most other things, too.
Just give 5 free queries of 4o/o3 or whatever and call it good.
And as a non-normie, I obviously didn't take its analysis seriously, and compared it to Grok and Gemini 2.5. The latter was the best.
What is happening?
I gave it a pdf of an engine manual recently and asked some questions, which it answered reasonably. It even pulled a schematic out for me, though it was the wrong one (it gave me a schematic for the CDI ignition variant that we first talked about, rather than the DSAI one we settled on later.)
FWIW,
This is what chatgpt gave me when I uploaded a lab report, it read the results back to me:
Here’s an interpretation of the blood test results you provided:
White Blood Cell Count (WBC) Value: 9.2 (Normal: 3.8 - 10.8 Thousand/uL)
Within the normal range, indicating no immediate signs of infection or inflammation.
Red Blood Cell Count (RBC) Value: 5.29 (Normal: 3.8 - 5.1 Million/uL)
Elevated (High). This could indicate dehydration, stress, or other conditions like polycythemia.
Hemoglobin Value: 10.9 (Normal: 11.7 - 15.5 g/dL)
Low. Suggests anemia, possibly due to iron deficiency or chronic disease.
Hematocrit Value: 36.0% (Normal: 35.0 - 45.0%)
Within the normal range, but on the lower side, supporting the presence of mild anemia.
Mean Corpuscular Volume (MCV) Value: 68.1 (Normal: 80.0 - 100.0 fL)
Low. Indicates microcytic anemia, often due to iron deficiency.
Mean Corpuscular Hemoglobin (MCH) Value: 20.6 (Normal: 27.0 - 33.0 pg)
Low. Suggests hypochromia (paler red blood cells), often associated with iron-deficiency anemia.
Mean Corpuscular Hemoglobin Concentration (MCHC) Value: 30.3 (Normal: 32.0 - 36.0 g/dL)
Slightly low. May reflect reduced hemoglobin in red blood cells, consistent with iron-deficiency anemia.
Red Cell Distribution Width (RDW) Value: 15.8% (Normal: 11.0 - 15.0%)
Elevated. Indicates variability in red blood cell size, common in iron-deficiency anemia.
Platelet Count Value: 397 (Normal: 140 - 400 Thousand/uL)
Normal, but on the higher side of the range.
Other Key Metrics Absolute Neutrophils, Lymphocytes, Monocytes, Eosinophils, Basophils: All within normal ranges, suggesting no significant abnormalities in immune cell populations.
Anisocytosis (1+): Indicates variation in red blood cell size.
Hypochromasia (1+): Suggests pale red blood cells, supporting iron-deficiency anemia.
Summary These results suggest iron-deficiency anemia, characterized by low hemoglobin, low MCV, low MCH, and high RDW. The elevated red blood cell count may reflect compensatory mechanisms or mild dehydration.
Your provider recommends a heart-healthy, low-fat diet, which is great for overall health. However, addressing the anemia might also involve increasing dietary iron or taking iron supplements.
The diagnosis is wrong, btw, I don't have iron deficiency. The anemia is caused by a genetic condition called thalassemia, which has been verified by genetic tests. You can use the Mentzer Index to differentiate the two on a simple CBC - https://www.mdcalc.com/calc/10534/mentzer-index
Mine numbers return a "probable diagnosis."
I was wondering if chatgpt would catch it, nope, it didn't. It did say that it was a possibility once I suggested it though.
I don't ever really use the term "thoroughly debunked" when referring to nutrition science; as you noted, a better term is that the claim is not supported by the evidence. I've seen enough things debunked and then rebunked to know that nutrition science is not really that accurate.
There was no reference in the report that the LLM might have pulled out to think otherwise.
The other stuff is good to have but ultimately a model that focuses on diagnosing medical conditions is going to be the most useful. Look - we aren't going to replace doctors anytime soon but it is good to have a second opinion from an LLM purely for diagnosis. I would hope it captures patterns that weren't observed before. This is exactly the sort of thing game that AI can beat a human at - large scale pattern recognition.
Physicians at this level serve the labor market, and everything they do is ordered to keeping you able-bodied and working and on the job and not taking sick days.
They have always been reluctant to dispense excuses from work, to document any sort of disability related trouble, or to give advice that does not involve more exercise or more medication.
I have honestly approached multiple doctors in multiple health systems to complain about fatigue, syncope, and exhaustion, and they all go to extraordinary lengths to deny that anything is wrong or that anything should change.
In fact, I’d prefer to be back on full work duties, but I’m still on light duty until my next appointment, assuming he restores me to full duty.
Providers who are reimbursed via Medicaid have zero incentive specific to Medicaid to not give out work “excuses”, document disabilities and so on. Generally speaking the same providers serve both Medicaid and non-Medicaid patients.
Perhaps there are some states where the Medicaid providers are really awful (California?).
There are a lot of innocuous things built into the healthcare system, like gating the cough syrup that gets you really high easily, behind a visit to a provider, that many people are just ignorant of as a virtue of the current setup.
When we disrupt fields that we are not experts in we often miss oceans of nuance.
"As an AI agent, a possible diagnosis is [xxx]. Ask your doctor about / look into [yyy™] for a possible solution!"
https://www.axios.com/2024/12/03/openai-ads-chatgpt
> OpenAI CFO Sarah Friar told the Financial Times that OpenAI is weighing the inclusion of ads in its products but wants to be "thoughtful about when and where we implement them."
It’s a pity they don’t support Greek language, keeping in mind that almost all medical terminology has Greek origins.
Anyhow, this is a step in the good direction and for sure it will aid many people looking for medical assistance via ChatGPT.
AI is a tool to transfer wealth from the middle class to the ultra wealthy. If there is a brief intermediary period where quality of life improves for the poor, it's a temporary coincidence that hasn't been optimized away yet.
Your. Costs. Will. Never. Go. Down. While. Maintaining. Equal. Service. In. The. Long. Term. That's. Not. What. Capitalists. Want.
you only need to look at this thread alone to prove your point. this is a race to the bottom that we're being accelerated towards by some of the worst people on earth.