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

491–500 of 513 posts

Re: GPT-4.1 in the API

#491

Post by karn97 »

brokencode wrote: post #314
greenchair wrote: post #308

Earlier quoted context omitted.

most people are building straightforward crud apps. no experimentation required.

Idk, it feels like this is what you’d expect versus the actual reality of building something. From my experience, even building on popular platforms, there are many bugs or poorly documented behaviors in core controls or APIs. And performance issues in particular can be difficult to fix without trial and error.

Not helpful when the llm knowledge cutoff is a year out of date and api and lib has been changed since

Re: GPT-4.1 in the API

#492

Post by yousif_123123 »

lxgr wrote: post #317

As a ChatGPT user, I'm weirdly happy that it's not available there yet. I already have to make a conscious choice between - 4o (can search the web, use Canvas, evaluate Python server-side, generate images, but has no chain of thought) - o3-mini (web search, CoT, canvas, but no image generation) - o1 (CoT, maybe better than o3, but no canvas or web search and also no images) - Deep Research (very powerful, but I have…

I do like the vinyl and analog amplifiers. I certainly hear the warmth in this case.

Re: GPT-4.1 in the API

#493

Post by th0ma5 »

Closi wrote: post #431
th0ma5 wrote: post #428

Earlier quoted context omitted.

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 erro…

The problem has always been that every token is suspect.

Re: GPT-4.1 in the API

#494

Post by xnx »

lxgr wrote: post #317

As a ChatGPT user, I'm weirdly happy that it's not available there yet. I already have to make a conscious choice between - 4o (can search the web, use Canvas, evaluate Python server-side, generate images, but has no chain of thought) - o3-mini (web search, CoT, canvas, but no image generation) - o1 (CoT, maybe better than o3, but no canvas or web search and also no images) - Deep Research (very powerful, but I have…

This sounds like whole lot of mental overhead to avoid using Gemini.

Re: GPT-4.1 in the API

#495

Post by huxley »

WorldPeas wrote: post #11
bakugo wrote: post #4

> We will also begin deprecating GPT‑4.5 Preview in the API, as GPT‑4.1 offers improved or similar performance on many key capabilities at much lower cost and latency. GPT‑4.5 Preview will be turned off in three months, on July 14, 2025, to allow time for developers to transition. Well, that didn't last long.

so we're going back... .4 of a gpt? make it make sense openai..

Think of 4.5 as being the lacklustre major upgrade to a software package, pick one maybe Photoshop or whatever. The 4.0 version is still available and most people are continuing to use it, then suddenly 4.0 gets a small upgrade which makes it considerably better and the vendor starts talking about how the real future is in 5.0.

I wish OpenAI had invented this but it’s not that uncommon.

Re: GPT-4.1 in the API

#496

Post by nebben64 »

NewUser76312 wrote: post #482

As a user I'm getting so confused as to what's the "best" for various categories. I don't have time/want to dig into benchmarks for different categories, look into the example data to see which best maps onto my current problems. The graphs presented don't even show a clear winner across all categories. The one with the biggest "number", GPT-4.5, isn't even in the best in most categories, actually it's like 3rd in a…

I think "best" is slightly subjective / user. But I understand your gripe. I think the only way is using them iteratively, settling on the one that best fits you / your use-case, whilst reading other peoples' experiences and getting a general vibe

Re: GPT-4.1 in the API

#497

Post by clbrmbr »

weird-eye-issue wrote: post #466
clbrmbr wrote: post #459

Earlier quoted context omitted.

If so, the loss of fidelity versus 4.5 is really noticeable and a loss for numerous applications. (Finding a vegan restaurant in a random city neighborhood, for example.)

In your example the LLM should not be responsible for that directly. It should be calling out to an API or search results to get accurate and up-to-date information (relatively speaking) and then use that context to generate a response

You should actually try it. The really big models (4 and 4.5, sadly not 4o) have truly breathtaking ability to dig up hidden gems that have a really low profile on the internet. The recommendations also seem to cut through all the SEO and review manipulation and deliver quality recommendations. It really all can be in one massive model.

Re: GPT-4.1 in the API

#498

Post by torginus »

benhurmarcel wrote: post #484
shortcord wrote: post #340

Earlier quoted context omitted.

Gemini 2.5 Pro is quite good at code. Has become my go to for use in Cursor. Claude 3.7 needs to be restrained too much.

I find that Gemini 2.5 Pro tends to produce working but over-complicated code more often than Claude 3.7.

Which might be a side-effect of the reasoning.

In my experience whenever these models solve a math or logic puzzle with reasoning, they generate extremely long and convoluted chains of thought which show up in the solution.

In contrast a human would come up with a solution with 2-3 steps. Perhaps something similar is going on here with the generated code.

Re: GPT-4.1 in the API

#499

Post by torginus »

ilrwbwrkhv wrote: post #386
modeless wrote: post #59

Numbers for SWE-bench Verified, Aider Polyglot, cost per million output tokens, output tokens per second, and knowledge cutoff month/year: SWE Aider Cost Fast Fresh Claude 3.7 70% 65% $15 77 8/24 Gemini 2.5 64% 69% $10 200 1/25 GPT-4.1 55% 53% $8 169 6/24 DeepSeek R1 49% 57% $2.2 22 7/24 Grok 3 Beta ? 53% $15 ? 11/24 I'm not sure this is really an apples-to-apples comparison as it may involve different test scaffoldi…

Yup GPT 4.1 isn't good at all compared to the others. I tried a bunch of different scenarios, for me the winners: Deepseek for general chat and research Claude 3.7 for coding Gemini 2.5 Pro experimental for deep research In terms of price Deepseek is still absolutely fire! OpenAI is in trouble honestly.

One task I do is I feed the models the text of entire books, and ask them various questions about it ('what happened in Chapter 4', 'what did character X do in the book' etc.).

GPT 4.1 is the first model that has provided a human-quality answer to these questions. It seems to be the first model that can follow plotlines, and character motivations accurately.

I'd say since text processing is a very important use case for LLMs, that's quite noteworthy.

Re: GPT-4.1 in the API

#500

Post by Aeroi »

The user shoudn't have to research which model is the best for them. OpenAI needs to do a better job in UX and putting the best model forward in chatgpt.
Post reply on HN