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

GPT-5.2

openai.com

Post reply on HN
Print view View original

861–870 of 1001 posts

Re: GPT-5.2

#861

Post by andybak »

ubutler wrote: post #731
mmaunder wrote: post #405

Weirdly, the blog announcement completely omits the actual new context window size which is 400,000: https://platform.openai.com/docs/models/gpt-5.2 Can I just say !!!!!!!! Hell yeah! Blog post indicates it's also much better at using the full context. Congrats OpenAI team. Huge day for you folks!! Started on Claude Code and like many of you, had that omg CC moment we all had. Then got greedy. Switched over to Codex…

> Weirdly, the blog announcement completely omits the actual new context window size which is 400,000: https://platform.openai.com/docs/models/gpt-5.2 As @lopuhin points out, they already claimed that context window for previous iterations of GPT-5. The funny thing is though, I'm on the business plan, and none of their models, not GPT-5, GPT-5.1, GPT-5.2, GPT-5.2 Extended Thinking, GPT-5.2 Pro, etc., can really handl…

Why would you put that whole python file in the context at all? Doesn't Codex work like Claude Code in this regard and use tools to find the correct parts of a larger file to read into context?

Re: GPT-5.2

#862

Post by andybak »

CodeCompost wrote: post #756

For the first time, I've actually hidden an AI story on HN. I can't even anymore. Sorry this is not going anywhere.

How this is different to any other post announcing an incremental improvement in an app or service?

Re: GPT-5.2

#863

Post by virtuosarmo »

svara wrote: post #765

In my experience, the best models are already nearly as good as you can be for a large fraction of what I personally use them for, which is basically as a more efficient search engine. The thing that would now make the biggest difference isn't "more intelligence", whatever that might mean, but better grounding. It's still a big issue that the models will make up plausible sounding but wrong or misleading explanations…

I've had better success finding information using Google Gemini vs. ChatGPT. I.e. someone mentions to me the name of someone or some company, but doesn't give the full details (i.e. Joe @ XYZ Company doing this, or this company with 10,000 people, in ABC industry)...sometimes i don't remember the full name. Gemini has been more effective for me in filling in the gaps and doing fuzzy search. I even asked ChatGPT why this was the case, and it affirmed my experience, saying that Gemini is better for these queries because of Search integration, Knowledge Graph, etc. Especially useful for recent role changes, which haven't been propagated through other channels on a widespread basis.

Re: GPT-5.2

#864

Post by svara »

phorkyas82 wrote: post #768
svara wrote: post #765

In my experience, the best models are already nearly as good as you can be for a large fraction of what I personally use them for, which is basically as a more efficient search engine. The thing that would now make the biggest difference isn't "more intelligence", whatever that might mean, but better grounding. It's still a big issue that the models will make up plausible sounding but wrong or misleading explanations…

Isn't that what no LLM can provide: being free of hallucinations?

A part of it is reproducing incorrect information in the training data as well.

One area that I've found to be a great example of this is sports science.

Depending on how you ask, you can get a response lifted from scientific literature, or the bro science one, even in the course of the same discussion.

It makes sense, both have answers to similar questions and are very commonly repeated online.

Re: GPT-5.2

#865

Post by ostacke »

EastLondonCoder wrote: post #859

I’ve been using GPT-4o and now 5.2 pretty much daily, mostly for creative and technical work. What helped me get more out of it was to stop thinking of it as a chatbot or knowledge engine, and instead try to model how it actually works on a structural level. The closest parallel I’ve found is Peter Gärdenfors’ work on conceptual spaces, where meaning isn’t symbolic but geometric. Fedorenko’s research on predictive se…

Interesting concept with conceptual spaces, but how does that affect how you work with LLM:s in practice?

Re: GPT-5.2

#866

Post by scrollop »

sanex wrote: post #560
scrollop wrote: post #388

Earlier quoted context omitted.

Why no grok 4.1 reasoning?

Do people other than Elon fans use grok? Honest question. I've never tried it.

I hate the guy, however grok scores high on arc-2 so it would be silly to not at least rank it.

Re: GPT-5.2

#867

Post by rl_shannon »

Isn't it delusional to only compare your models against your own previous variants? Where is an actual comparison with Google, Anthropic, OSS Models

Re: GPT-5.2

#868

Post by d-lisp »

lostmsu wrote: post #772
d-lisp wrote: post #745

Earlier quoted context omitted.

Most non tech people I talked with don't care at all about LLMs. They also are not impressed at all ("Okay, that's like google and internet").

Old people? I think it would be hard to find a lot of people under 20 who don't use ChatGPT daily. At least among ones that are still studying.

People older than 25 or 30 maybe.

It would be funny that in the end, the most use is made by student cheating at uni.

Re: GPT-5.2

#869

Post by zild3d »

rl_shannon wrote: post #867

Isn't it delusional to only compare your models against your own previous variants? Where is an actual comparison with Google, Anthropic, OSS Models

it's the best ____ we've ever made

Re: GPT-5.2

#870

Post by ryoshu »

biofox wrote: post #830
stacktrace wrote: post #785

Earlier quoted context omitted.

> It's still a big issue that the models will make up plausible sounding but wrong or misleading explanations for things, and verifying their claims ends up taking time. And if it's a topic you don't care about enough, you might just end up misinformed. Exactly! One important thing LLMs have made me realise deeply is "No information" is better than false information. The way LLMs pull out completely incorrect explana…

I ask for confidence scores in my custom instructions / prompts, and LLMs do surprisingly well at estimating their own knowledge most of the time.

LLMs fail at causal accuracy. It's a fundamental problem with how they work.
Post reply on HN