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

461–470 of 1001 posts

Re: GPT-5.2

#461

Post by energy123 »

lopuhin wrote: post #453
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…

Context window size of 400k is not new, gpt-5, 5.1, 5-mini, etc. have the same. But they do claim they improved long context performance which if true would be great.

But 400k was never usable in ChatGPT Plus/Pro subscriptions. It was nerfed down to 60-100k. If you submitted too long of a prompt they deleted the tokens on the end of your prompt before calling the model. Or if the chat got too long (still below 100k however) they deleted your first messages. This was 3 months ago.

Can someone with an active sub check whether we can submit a full 400k prompt (or at least 200k) and there is no prompt truncatation in the backend? I don't mean attaching a file which uses RAG.

Re: GPT-5.2

#462

Post by osn9363739 »

ionwake wrote: post #83
JanSt wrote: post #42

The benchmarks are very impressive. Codex and Opus 4.5 are really good coders already and they keep getting better. No wall yet and I think we might have crossed the threshold of models being as good or better than most engineers already. GDPval will be an interesting benchmark and I'll happily use the new model to test spreadsheet (and other office work) capabilities. If they can going like this just a little bit fu…

it was only about 2-3 weeks when several HNers told me "nah you better re-check your code", when I explained I have over 2 decades xp of coding, yet have not manually edited code (in memory) for the last 6 or so months, whilst performing daily 12 hour daily vibe code seshes

Do you have any examples or are your project oss or anything like that? Because I want to believe, but I have people I work with that say and try the same thing (no manual coding), and their work is now terrible.

Re: GPT-5.2

#463

Post by Der_Einzige »

radicaldreamer wrote: post #337
solarkraft wrote: post #306

Earlier quoted context omitted.

> Only downsides are in the polish department What an understatement. It has me thinking „man, fuck this“ on the daily. Just today it spontaneously lost an entire 20-30 minutes long thread and it was far from the first time. It basically does it any time you interrupt it in any way. It’s straight up data loss. It’s kind of a typical Google product in that it feels more like a tech demo than a product. It has theoreti…

Google’s standard problem is that they don’t even use their own products. Their Pixel and Android team rocks iPhones on the daily, for example.

That’s because they will be bullied out of the dating market if they have a “green bubble”.

Re: GPT-5.2

#464

Post by tekacs »

freedomben wrote: post #443
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…

I haven't done a ton of testing due to cost, but so far I've actually gotten worse results with xhigh than high with gpt-5.1-codex-max. Made me wonder if it was somehow a PEBKAC error. Have you done much comparison between high and xhigh?

I found the same with Max xhigh. To the point that I switched back to just 5.1 High from 5.1 Codex Max. Maybe I should’ve tried Max high first.

Re: GPT-5.2

#466

Post by jaimex2 »

They just keep flogging that dead horse.

The winner in this race will be whoever gets small local models to perform as well on consumer hardware. It'll also pop the tech bubble in the US.

Re: GPT-5.2

#467

Post by dudeinhawaii »

freedomben wrote: post #443
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…

I haven't done a ton of testing due to cost, but so far I've actually gotten worse results with xhigh than high with gpt-5.1-codex-max. Made me wonder if it was somehow a PEBKAC error. Have you done much comparison between high and xhigh?

This is one of those areas where I think it's about the complexity of the task. What I mean is, if you set codex to xhigh by default, you're wasting compute. IF you're setting it at xhigh when troubleshooting a complex memory bug or something, you're presumably more likely to get a quality response.

I think in general, medium ends up being the best all-purpose setting while high+ are good for single task deep-drive. Or at least that has been my experience so far. You can theoretically let with work longer on a harder task as well.

A lot appears to depend on the problem and problem domain unfortunately.

I've used max in problem sets as diverse as "troubleshooting Cyberpunk mods" and figuring out a race condition in a server backend. In those cases, it did a pretty good job of exhausting available data (finding all available logs, digging into lua files), and narrowing a bug that every other model failed to get.

I guess in some sense you have to know from the onset that it's a "hard problem". That in and of itself is subjective.

Re: GPT-5.2

#468

Post by johnwheeler »

I'm not interested in using OpenAI anymore because Sam Altman is so untrustworthy. All you see on X.com is him and Greg Brockman kissing David Sacks' ass, trying to make inroads with him, asking Disney for investments, and shit. Are you kidding? Who wants to support these clowns? Let's let Google win. Let's let Anthropic win. Anyone but Sam Altman.

Re: GPT-5.2

#469

Post by malfist »

AstroBen wrote: post #408
malfist wrote: post #386

Earlier quoted context omitted.

If I ask you a question and you don't have enough information to answer, you don't confidently give me an answer, you say you don't know. I might not know exactly how many USB ports this motherboard has, but I wouldn't select a set of 4 and declare it to be a stacked pair.

No-one should have the expectation LLMs are giving correct answers 100% of the time. It's inherent to the tech for them to be confidently wrong Code needs to be checked References need to be checked Any facts or claims need to be checked

According to the benchmarks here they're claiming up to 97% accuracy. That ought to be good enough to trust them right?

Or maybe these benchmarks are all wrong

Re: GPT-5.2

#470

Post by 0xdeafbeef »

noname120 wrote: post #392
onraglanroad wrote: post #333

I suppose this is as good a place as any to mention this. I've now met two different devs who complained about the weird responses from their LLM of choice, and it turned out they were using a single session for everything. From recipes for the night, presents for the wife and then into programming issues the next day. Don't do that. The whole context is sent on queries to the LLM, so start a new chat for each topic.…

Problem is that by default ChatGPT has the “Reference chat history” option enabled in the Memory options. This causes any previous conversation to leak into the current one. Just creating a new conversation is not enough, you also need to disable that option.

Only your questions are in it though
Post reply on HN