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

71–80 of 513 posts

Re: GPT-4.1 in the API

#71

Post by darksaints »

codingwagie wrote: post #10

GPT-4.1 probably is a distilled version of GPT-4.5 I dont understand the constant complaining about naming conventions. The number system differentiates the models based on capability, any other method would not do that. After ten models with random names like "gemini", "nebula" you would have no idea which is which. Its a low IQ take. You dont name new versions of software as completely different software Also, Yest…

[flagged]

Re: GPT-4.1 in the API

#72

Post by oofbaroomf »

jfoster wrote: post #35
polytely wrote: post #18

It seems that OpenAI is really differentiating itself in the AI market by developing the most incomprehensible product names in the history of software.

I wonder how they decide whether the o or the digit needs to come first. (eg. o3 vs 4o)

Reasoning models have the o first, non-reasoners have the digit first.

Re: GPT-4.1 in the API

#73

Post by greenavocado »

oofbaroomf wrote: post #65

I'm not really bullish on OpenAI. Why would they only compare with their own models? The only explanation could be that they aren't as competitive with other labs as they were before.

See figure 1 for up-to-date benchmarks https://github.com/KCORES/kcores-llm-arena

(Direct Link) https://raw.githubusercontent.com/KCORES/kcores-llm-arena/re...

Re: GPT-4.1 in the API

#74

Post by poormathskills »

oofbaroomf wrote: post #65

I'm not really bullish on OpenAI. Why would they only compare with their own models? The only explanation could be that they aren't as competitive with other labs as they were before.

Go look at their past blog posts. OpenAI only ever benchmarks against their own models.

Re: GPT-4.1 in the API

#75

Post by elashri »

Are there any benchmarks or someone who did tests of performance of using this long max token models in scenarios where you actually use more of this token limit?

I found from my experience with Gemini models that after ~200k that the quality drops and that it basically doesn't keep track of things. But I don't have any numbers or systematic study of this behavior.

I think all providers who announce increased max token limit should address that. Because I don't think it is useful to just say that max allowed tokens are 1M when you basically cannot use anything near that in practice.

Re: GPT-4.1 in the API

#78

Post by sbarre »

exizt88 wrote: post #56
Tiberium wrote: post #42

Very important note: >Note that GPT‑4.1 will only be available via the API. In ChatGPT, many of the improvements in instruction following, coding, and intelligence have been gradually incorporated into the latest version If anyone here doesn't know, OpenAI does offer the ChatGPT model version in the API as chatgpt-4o-latest, but it's bad because they continuously update it so businesses can't reliably rely on it bein…

> chatgpt-4o-latest, but it's bad because they continuously update it Version explicitly marked as "latest" being continuously updated it? Crazy.

No one's arguing that it's improperly labelled, but if you're going to use it via API, you might want consistency over bleeding edge.

Re: GPT-4.1 in the API

#80

Post by School-Cotton »

henlobenlo wrote: post #61
School-Cotton wrote: post #45

Earlier quoted context omitted.

Btw, as someone who agrees with your point, what’s the actual answer to this?

Whats the problem, for the layman it doesnt actually matter, and for the experts, its usually very obvious which model to use.

That’s not true. I’m a layman and 4.5 is obviously better than 4o for me, definitely enough to matter.
Post reply on HN