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

591–600 of 1001 posts

Re: GPT-5.2

#591

Post by simonw »

alechewitt wrote: post #578
simonw wrote: post #125

Wow, there's a lot going on with this pelican riding a bicycle: https://gist.github.com/simonw/c31d7afc95fe6b40506a9562b5e83...

Nice work on these benchmarks Simon. I’ve followed your blog closely since your great talk at the AI Engineers World Fair, and I want to say thank you for all the high quality content you share for free. It’s become my primary source for keeping up to date. I’ve been working on a few benchmarks to test how well LLMs can recreate interfaces from screenshots. ( https://github.com/alechewitt/llm-ui-challenge ). From my…

That is a very good benchmark. Interesting to see GPT-5.2 delivering on the promise of better vision support there.

Re: GPT-5.2

#592

Post by sam345 »

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 inexcusable.

Re: GPT-5.2

#593

Post by tobias2014 »

enlyth wrote: post #179
Tiberium wrote: post #35

Earlier quoted context omitted.

They did compare it to other models: https://x.com/OpenAI/status/1999182104362668275 https://i.imgur.com/e0iB8KC.png

This looks cherry-picked, for example Claude Opus had a higher score on SWE-Bench Verified so they conveniently left it out, also GDPval is literally a benchmark made by OpenAI

And who believes that the difference between 91.9% and 92.4% is significant in these benchmarks? Clearly these have margins of error that are swept under the rug.

Re: GPT-5.2

#594

Post by tiahura »

redhed wrote: post #485
gordonhart wrote: post #477

Earlier quoted context omitted.

> Makes no sense to me why this is the default. You’re probably pretty far from the average user, who thinks “AI is so dumb” because it doesn’t remember what you told it yesterday.

I was thinking more people would be annoyed by it bringing up unrelated conversations, thinking more I'd say you're probably right that more people are expecting it to remember everything they say.

It’s not that it brings it up in unrelated conversations, it’s that it nudges related conversations in unwanted directions.

Re: GPT-5.2

#595

Post by mmaunder »

Kim_Bruning wrote: post #550
mmaunder wrote: post #389

Earlier quoted context omitted.

Then you haven't used Gemini CLI with Gemini 3 hard enough. It's a genius psychopath. The raw IQ that Gemini has is incredible. Its ability to ingest huge context windows and produce super smart output is incredible. But the bias towards action, absolutely ignoring user guidance, tendency to produce garbage output that looks like 1990s modem line noise, and its propensity to outright ignore instructions make it unusa…

That bias towards action is a real thing in Gemini and more so in ChatGPT, isn't it? Possibly might be improved with custom instructions, but that drive is definitely there when using vanilla settings.

Yeah it's a weird mix of issues with the backend model and issues with the CLI client and its prompts. What makes it hard for them is the teams aren't talking to each other. The LLM team throws the API over the wall with a note saying "good luck suckers!".

Re: GPT-5.2

#596

Post by 8cvor6j844qw_d6 »

What the current preferred subscription on AI?

OpenAI and Anthrophic is my current preference. Looking forward to know what others use.

Claude Code for coding assistance and cross-checking my work. OpenAI for second opinion on my high-level decisions.

Re: GPT-5.2

#597

Post by Max-Limelihood »

p_ing wrote: post #546
sundarurfriend wrote: post #363

Earlier quoted context omitted.

ChatGPT web UI was also like this for the longest time, until a few months ago: all sorts of random UI bugs leading either to data loss or misleading UI state. Interrupting still is very flaky there too. And on the mobile app, if you move away from the app while it's taking time to think, its state would somehow desync from the actual backend thinking state, and get stuck randomly; sometimes restarting the app fixes…

> ChatGPT web UI was also like this for the longest time Copilot Chat has been perfect in this respect. It's currently GPT 5.0, moving to 5.1 over the next month or so, but at least I've never lost an (even old) conversation since those reside in an Exchange mailbox.

I lost thousands of conversations I'd had back in the move from "Bing" to "Copilot". Moved straight to Claude and never touched a GPT again.

Re: GPT-5.2

#598

Post by deaux »

nbardy wrote: post #398

Those arc agi 2 improvements are insane. Thats especially encouraging to me because those are all about generalization. 5 and 5.1 both felt overfit and would break down and be stubborn when you got them outside their lane. As opposed to Opus 4.5 which is lovely at self correcting. It’s one of those things you really feel in the model rather than whether it can tackle a harder problem or not, but rather can I go back…

> 5 and 5.1 both felt overfit and would break down and be stubborn when you got them outside their lane. As opposed to Opus 4.5 which is lovely at self correcting.

This is simply the "openness vs directive-following" spectrum, which as a side-effect results in the sycophancy spectrum, which still none of them have found an answer to.

Recent GPT models follow directives more closely than Claude models, and are less sycophantic. Even Claude 4.5 models are still somewhat prone to "You're absolutely right!". GPT 5+ (API) models never do this. The byproduct is that the former are willing to self-correct, and the latter is more stubborn.

Re: GPT-5.2

#599

Post by deaux »

jstummbillig wrote: post #90
xd1936 wrote: post #68

> While GPT‑5.2 will work well out of the box in Codex, we expect to release a version of GPT‑5.2 optimized for Codex in the coming weeks. https://openai.com/index/introducing-gpt-5-2/

> For coding tasks, GPT-5.1-Codex-Max is a faster, more capable, and more token-efficient coding variant Hm, yeah, strange. You would not be able to tell, looking at every chart on the page. Obviously not a gotcha, they put it on the page themselves after all, but how does that make sense with those benchmarks?

Looks like they removed that line.

Re: GPT-5.2

#600

Post by what-the-grump »

bgwalter wrote: post #557
mmaunder wrote: post #501

Earlier quoted context omitted.

My name is Mark Maunder. Not the fisheries expert. The other one when you google me. I’m 51 and as skeptical as you when it comes to tech. I’m the CTO of a well known cybersecurity company and merely a user of AI. Since you critiqued my post, allow me to reciprocate: I sense the same deflector shields in you as many others here. I’d suggest embracing these products with a sense of optimism until proven otherwise and…

I have tried the models and in domains I know well they are pathetic. They remove all nuance, make errors that non-experts do not notice and generally produce horrible code. It is even worse in non-programming domains, where they chop up 100 websites and serve you incorrect bland slop. If you are using them as a search helper, that sometimes works, though 2010 Google produced better results. Oracle dropped 11% today…

You pretend that humans don’t produce slop?

I can recognize the short comings of AI code but it can produce a mock or a full blown class before I can find a place to save the file it produced.

Pretending that we are all busy writing novelty and genius is silly, 99% are writing for CRUD tasks and basic business flows, the code isn’t going to be perfect it doesn’t need to be but it will get the job done.

All the logical gotchas of the work flows that you’d be refactoring for hours are done in minutes.

Use pro with search… are it going to read 200 pages of documentation in 7 minutes come up with a conclusion and validate it or invalidate it in another 5? No you still trying accept the cookie prompt on your 6th result.

You might as well join the flat earth society if you still think that AI can’t help you complete day to day tasks.

Post reply on HN