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

From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

fertrevino.com

Post reply on HN
Print view View original

21–30 of 102 posts

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#21

Post by furyofantares »

ares623 wrote: post #16
SequoiaHope wrote: post #14

Earlier quoted context omitted.

What you describe is a person selecting the best results, but if you can get better results one shot with that option enabled, it’s worth testing and reporting results.

I get that. But then if that option doesn't help, what I've seen is that the next followup is inevitably "have you tried doing/prompting x instead of y"

Something I've experienced with multiple new model releases is plugging them into my app makes my app worse. Then I do a bunch of work on prompts and now my app is better than ever. And it's not like the prompts are just better and make the old model work better too - usually the new prompts make the old model worse or there isn't any change.

So it makes sense to me that you should try until you get the results you want (or fail to do so). And it makes sense to ask people what they've tried. I haven't done the work yet to try this for gpt5 and am not that optimistic, but it is possible it will turn out this way again.

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#22

Post by TrainedMonkey »

aresant wrote: post #11

Feels like a mixed bag vs regression? eg - GPT-5 beats GPT-4 on factual recall + reasoning (HeadQA, Medbullets, MedCalc). But then slips on structured queries (EHRSQL), fairness (RaceBias), evidence QA (PubMedQA). Hallucination resistance better but only modestly. Latency seems uneven (maybe more testing?) faster on long tasks, slower on short ones.

GPT-5 feels like cost engineering. The model is incrementally better, but they are optimizing for least amount of compute. I am guessing investors love that.

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#23

Post by degamad »

teaearlgraycold wrote: post #12
username135 wrote: post #10

I wonder what changed with the models that created regression?

Not sure but with each release it feels like they’re just wiping the dirt around and not actually cleaning.

Obligxkcd: https://xkcd.com/1838/

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#24

Post by narrator »

TrainedMonkey wrote: post #22
aresant wrote: post #11

Feels like a mixed bag vs regression? eg - GPT-5 beats GPT-4 on factual recall + reasoning (HeadQA, Medbullets, MedCalc). But then slips on structured queries (EHRSQL), fairness (RaceBias), evidence QA (PubMedQA). Hallucination resistance better but only modestly. Latency seems uneven (maybe more testing?) faster on long tasks, slower on short ones.

GPT-5 feels like cost engineering. The model is incrementally better, but they are optimizing for least amount of compute. I am guessing investors love that.

I agree. I have found GPT-5 significantly worse on medical queries. It feels like it skips important details and is much worse than o3, IMHO. I have heard good things about GPT-5 Pro, but that's not cheap.

I wonder if part of the degraded performance is where they think you're going into a dangerous area and they get more and more vague, for example like they demoed on launch day with the fireworks example. It gets very vague when talking about non-abusable prescription drugs for example. I wonder if that sort of nerfing gradient is affecting medical queries.

After seeing some painfully bad results, I'm currently using Grok4 for medical queries with a lot of success.

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#25

Post by dcre »

aprilthird2021 wrote: post #18
dcre wrote: post #15

Earlier quoted context omitted.

This is not a good analogy because reasoning models are not choosing the best from a set of attempts based on knowledge of the correct answer. It really is more like what it sounds like: “did you think about it longer until you ruled out various doubts and became more confident?” Of course nobody knows quite why directing more computation in this way makes them better, and nobody seems to take the reasoning trace too…

> Of course nobody knows quite why directing more computation in this way makes them better, and nobody seems to take the reasoning trace too seriously as a record of what is happening. But it is clear that it works! One thing it's hard to wrap my head around is that we are giving more and more trust to something we don't understand with the assumption (often unchecked) that it just works. Basically your refrain is u…

Trusting things to work based on practical experience and without formal verification is the norm rather than the exception. In formal contexts like software development people have the means to evaluate and use good judgment.

I am much more worried about the problem where LLMs are actively misleading low-info users into thinking they’re people, especially children and old people.

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#26

Post by yieldcrv »

TrainedMonkey wrote: post #22
aresant wrote: post #11

Feels like a mixed bag vs regression? eg - GPT-5 beats GPT-4 on factual recall + reasoning (HeadQA, Medbullets, MedCalc). But then slips on structured queries (EHRSQL), fairness (RaceBias), evidence QA (PubMedQA). Hallucination resistance better but only modestly. Latency seems uneven (maybe more testing?) faster on long tasks, slower on short ones.

GPT-5 feels like cost engineering. The model is incrementally better, but they are optimizing for least amount of compute. I am guessing investors love that.

Yeah look at their open source models and how you get such high parameters in such low vram

Its impressive but a regression for now, in direct comparison to just high parameter model

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#27

Post by Art9681 »

ares623 wrote: post #16
SequoiaHope wrote: post #14

Earlier quoted context omitted.

What you describe is a person selecting the best results, but if you can get better results one shot with that option enabled, it’s worth testing and reporting results.

I get that. But then if that option doesn't help, what I've seen is that the next followup is inevitably "have you tried doing/prompting x instead of y"

It can be summarized as "Did you RTFM?". One shouldn't expect optimal results if the time and effort wasn't invested in learning the tool, any tool. LLMs are no different. GPT-5 isn't one model, it's 6: gpt-5, gpt-5 mini, gpt-nano. Each takes high|medium|low configurations. Anyone who is serious about measuring model capability would go for the best configuration, especially in medicine.

I skimmed through the paper and I didnt see any mention of what parameters they used other than they use gpt-5 via the API.

What was the reasoning_effort? verbosity? temperature?

These things matter.

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#28

Post by brendoelfrendo »

dcre wrote: post #15
ares623 wrote: post #13

Earlier quoted context omitted.

Sorry, not directed at you specifically. But every time I see questions like this I can’t help but rephrase in my head: “Did you try running it over and over until you got the results you wanted?”

This is not a good analogy because reasoning models are not choosing the best from a set of attempts based on knowledge of the correct answer. It really is more like what it sounds like: “did you think about it longer until you ruled out various doubts and became more confident?” Of course nobody knows quite why directing more computation in this way makes them better, and nobody seems to take the reasoning trace too…

Bad news: it doesn't seem to work as well as you might think: https://arxiv.org/pdf/2508.01191

As one might expect, because the AI isn't actually thinking, it's just spending more tokens on the problem. This sometimes leads to the desired outcome but the phenomenon is very brittle and disappears when the AI is pushed outside the bounds of its training.

To quote their discussion, "CoT is not a mechanism for genuine logical inference but rather a sophisticated form of structured pattern matching, fundamentally bounded by the data distribution seen during training. When pushed even slightly beyond this distribution, its performance degrades significantly, exposing the superficial nature of the “reasoning” it produces."

Re: From GPT-4 to GPT-5: Measuring progress through MedHELM [pdf]

#29

Post by credit_guy »

Here's my experience: for some coding tasks where GPT 4.1, Claude Sonnet 4, Gemini 2.5 Pro were just spinning for hours and hours and getting nowhere, GPT 5 just did the job without a fuss. So, I switched immediately to GPT 5, and never looked back. Or at least I never looked back until I found out that my company has some Copilot limits for premium models and I blew through the limit. So now I keep my context small, use GPT 5 mini when possible, and when it's not working I move to the full GPT 5. Strangely, it feels like GPT 5 mini can corrupt the full GPT 5, so sometimes I need to go back to Sonnet 4 to get unstuck. To each their own, but I consider GPT 5 a fairly bit move forward in the space of coding assistants.
Post reply on HN