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

GPT-4.1 in the API

openai.com

Post reply on HN
Print view View original

431–440 of 513 posts

Re: GPT-4.1 in the API

#431

Post by Closi »

th0ma5 wrote: post #428
RussianCow wrote: post #312

Earlier quoted context omitted.

LLMs are still very young. We'll get there in time. I don't see how it's any different than optimizing for new CPU/GPU architectures other than the fact that the latter is now a decades-old practice.

Not to pick on you, but this is exactly the objectionable handwaving. What makes you think we'll get there? The kinds of errors that these technologies make have not changed, and anything that anyone learns about how to make them better changes dramatically from moment to moment and no one can really control that. It is different because those other things were deterministic ...

In comp sci it’s been deterministic, but in other science disciplines (eg medicine) it’s not. Also in lots of science it looks non-deterministic until it’s not (eg medicine is theoretically deterministic, but you have to reason about it experimentally and with probabilities - doesn’t mean novel drugs aren’t technological advancements).

And while the kind of errors hasn’t changed, the quantity and severity of the errors has dropped dramatically in a relatively short span of time.

Re: GPT-4.1 in the API

#433

Post by namaria »

qingcharles wrote: post #401
throwup238 wrote: post #337

Earlier quoted context omitted.

> - Deep Research (very powerful, but I have only 10 attempts per month, so I end up using roughly zero) Same here, which is a real shame. I've switched to DeepResearch with Gemini 2.5 Pro over the last few days where paid users have a 20/day limit instead of 10/month and it's been great, especially since now Gemini seems to browse 10x more pages than OpenAI Deep Research (on the order of 200-400 pages versus 20-40).…

Wow, I wondered what the limit was. I never checked, but I've been using it hesitantly since I burn up OpenAI's limit as soon as it resets. Thanks for the clarity. I'm all-in on Deep Research. It can conduct research on niche historical topics that have no central articles in minutes, which typically were taking me days or weeks to delve into.

I like Deep Research but as a historian I have to tell you. I've used it for history themes to calibrated my expectations and it is a nice tool but... It can easily brush over nuanced discussions and just return folk wisdom from blogs.

What I love most about history is it has lots of irreducible complexity and poring over the literature, both primary and secondary sources, is often the only way to develop an understanding.

Re: GPT-4.1 in the API

#434

Post by antman »

qingcharles wrote: post #401
throwup238 wrote: post #337

Earlier quoted context omitted.

> - Deep Research (very powerful, but I have only 10 attempts per month, so I end up using roughly zero) Same here, which is a real shame. I've switched to DeepResearch with Gemini 2.5 Pro over the last few days where paid users have a 20/day limit instead of 10/month and it's been great, especially since now Gemini seems to browse 10x more pages than OpenAI Deep Research (on the order of 200-400 pages versus 20-40).…

Wow, I wondered what the limit was. I never checked, but I've been using it hesitantly since I burn up OpenAI's limit as soon as it resets. Thanks for the clarity. I'm all-in on Deep Research. It can conduct research on niche historical topics that have no central articles in minutes, which typically were taking me days or weeks to delve into.

Interesting use case. My problem is that for niche subjects the crawled pages probably have not captured the information and the response becomes irrelevant. Perhaps gemini will produce better results just because it takes into account much more pages

Re: GPT-4.1 in the API

#435

Post by dev1ycan »

999900000999 wrote: post #227

Have they implemented "I don't know" yet. I probably spend 100$ a month on AI coding, and it's great at small straightforward tasks. Drop it into a larger codebase and it'll get confused. Even if the same tool built it in the first place due to context limits. Then again, the way things are rapidly improving I suspect I can wait 6 months and they'll have a model that can do what I want.

bahahaha spoken like someone who spends $100 to do the task a single semi decent software developer (yourself) should be able to do for... $0

Re: GPT-4.1 in the API

#436

Post by tekacs »

namaria wrote: post #433
qingcharles wrote: post #401

Earlier quoted context omitted.

Wow, I wondered what the limit was. I never checked, but I've been using it hesitantly since I burn up OpenAI's limit as soon as it resets. Thanks for the clarity. I'm all-in on Deep Research. It can conduct research on niche historical topics that have no central articles in minutes, which typically were taking me days or weeks to delve into.

I like Deep Research but as a historian I have to tell you. I've used it for history themes to calibrated my expectations and it is a nice tool but... It can easily brush over nuanced discussions and just return folk wisdom from blogs. What I love most about history is it has lots of irreducible complexity and poring over the literature, both primary and secondary sources, is often the only way to develop an understa…

When I've wanted it to not do things like this, I've had good luck directing it to... not look at those sources.

For example when I've wanted to understand an unfolding story better than the news, I've told it to ignore the media and go only to original sources (e.g. speech transcripts, material written by the people involved, etc.)

Re: GPT-4.1 in the API

#437

Post by elAhmo »

coldcache wrote: post #146
marsh_mellow wrote: post #142

From OpenAI's announcement: > Qodo tested GPT‑4.1 head-to-head against Claude Sonnet 3.7 on generating high-quality code reviews from GitHub pull requests. Across 200 real-world pull requests with the same prompts and conditions, they found that GPT‑4.1 produced the better suggestion in 55% of cases. Notably, they found that GPT‑4.1 excels at both precision (knowing when not to make suggestions) and comprehensiveness…

Interesting link. Worth noting that the pull requests were judged by o3-mini. Further, I'm not sure that 55% vs 45% is a huge difference.

I first read it as 55% better, which sounds significantly higher than ~22% which they report here. Sounds misleading.

Re: GPT-4.1 in the API

#438

Post by elAhmo »

Company worth hundreds of billions of dollars, on paper at least, has one of the worst naming schemes for their products in the recent history.

Sam acknowledged this a few months ago, but with another release not really bringing any clarity, this is getting ridiculous now.

Re: GPT-4.1 in the API

#439

Post by namaria »

tekacs wrote: post #436
namaria wrote: post #433

Earlier quoted context omitted.

I like Deep Research but as a historian I have to tell you. I've used it for history themes to calibrated my expectations and it is a nice tool but... It can easily brush over nuanced discussions and just return folk wisdom from blogs. What I love most about history is it has lots of irreducible complexity and poring over the literature, both primary and secondary sources, is often the only way to develop an understa…

When I've wanted it to not do things like this, I've had good luck directing it to... not look at those sources. For example when I've wanted to understand an unfolding story better than the news, I've told it to ignore the media and go only to original sources (e.g. speech transcripts, material written by the people involved, etc.)

Deep Search is pretty good for current news stories. I've had it analyze some legal developments in a European nation recently and it gave me a great overview.

Re: GPT-4.1 in the API

#440

Post by intended »

If reasoning models are any good, then can they figure out overpowered builds for poe2?

Wait, wouldn’t this be a decent test for reasoning ?

Every patch changes things, and there’s massive complexity with the various interactions between items, uniques, runes, and more.

Post reply on HN