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

441–450 of 1001 posts

Re: GPT-5.2

#441

Post by ssl-3 »

onethought wrote: post #344
radicaldreamer wrote: post #337

Earlier quoted context omitted.

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.

I mean there is benefit to understanding competitor well as well?

There certainly is.

To posit a scenario: I would expect General Motors to buy some Ford vehicles to test and play around with and use. There's always stuff to learn about what the competition has done (whether right, wrong, or indifferent).

But I also expect the parking lots used by employees at any GM design facility in the world to be mostly full of General Motors products, not Fords.

Re: GPT-5.2

#442

Post by whimsicalism »

Tiberium wrote: post #35
minadotcom wrote: post #22

They used to compare to competing models from Anthropic, Google DeepMind, DeepSeek, etc. Seems that now they only compare to their own models. Does this mean that the GPT-series is performing worse than its competitors (given the "code red" at OpenAI)?

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

uh oh, where did SWE bench go :D

Re: GPT-5.2

#443

Post by freedomben »

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?

Re: GPT-5.2

#444

Post by hexaga »

hnuser123456 wrote: post #217
BoppreH wrote: post #190

Earlier quoted context omitted.

That would be a laudable goal, but I feel like it's contradicted by the text: > Even on a low-quality image, GPT‑5.2 identifies the main regions and places boxes that roughly match the true locations of each component I would not consider it to have "identified the main regions" or to have "roughly matched the true locations" when ~1/3 of the boxes have incorrect labels . The remark "even on a low-quality image" is n…

Yeah, what it's calling RAM slots is the CMOS battery. What it's calling the PCIE slot is the interior side of the DB-9 connector. RAM slots and PCIE slots are not even visible in the image.

It just overlaid a typical ATX pattern across the motherboard-like parts of the image, even if that's not really what the image is showing. I don't think it's worthwhile to consider this a 'local recognition failure', as if it just happened to mistake CMOS for RAM slots.

Imagine it as a markdown response:

# Why this is an ATX layout motherboard (Honest assessment, straight to the point, *NO* hallucinations)

1. *RAM* as you can clearly see, the RAM slots are to the right of the CPU, so it's obviously ATX

2. *PCIE* the clearly visible PCIE slots are right there at the bottom of the image, so this definitely cannot be anything except an ATX motherboard

3. ... etc more stuff that is supported only by force of preconception

--

It's just meta signaling gone off the rails. Something in their post-training pipeline is obviously vulnerable given how absolutely saturated with it their model outputs are.

Troubling that the behavior generalizes to image labeling, but not particularly surprising. This has been a visible problem at least since o1, and the lack of change tells me they do not have a real solution.

Re: GPT-5.2

#446

Post by azan_ »

tenpoundhammer wrote: post #295

I have been using chatGPT a ton over the last months and paying the subscription. Used it for coding, news, stock analysis, daily problems, and a whatever I could think of. I decided to give Gemini a go when version three came out to great reviews. Gemini handles every single one of my uses cases much better and consistently gives better answers. This is especially true for situations were searching the web for curre…

That's interesting. I've got completely different impression. Every time I use Gemini I'm surprised how bad it is. My main complaint is that Gemini is too lazy.

Re: GPT-5.2

#448

Post by Forgeties79 »

onethought wrote: post #344
radicaldreamer wrote: post #337

Earlier quoted context omitted.

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.

I mean there is benefit to understanding competitor well as well?

I wonder how many apple employees walk in to the office with android phones

Re: GPT-5.2

#449

Post by concinds »

didibus wrote: post #418
tenpoundhammer wrote: post #295

I have been using chatGPT a ton over the last months and paying the subscription. Used it for coding, news, stock analysis, daily problems, and a whatever I could think of. I decided to give Gemini a go when version three came out to great reviews. Gemini handles every single one of my uses cases much better and consistently gives better answers. This is especially true for situations were searching the web for curre…

> Overall, my conclusion is that ChatGPT has lost and won't catch up because of the search integration strength. Depends, even though Gemini 3 is a bit better than GPT5.1, the quality of the ChatGPT apps themselves (mobile, web) have kept me a subscriber to it. I think Google needs to not-google themselves into a poor app experience here, because the models are very close and will probably continue to just pass each…

The ChatGPT Mac app especially feels much nicer to use. I like Gemini more due to the context window but I doubt Google will ever create a native Mac app.

Re: GPT-5.2

#450

Post by woeirua »

causal wrote: post #47
josalhor wrote: post #11

From GPT 5.1 Thinking: ARC AGI v2: 17.6% -> 52.9% SWE Verified: 76.3% -> 80% That's pretty good!

That ARC AGI score is a little suspicious. That's a really tough for AI benchmark. Curious if there were improvements to the test harness because that's a wild jump in general problem solving ability for an incremental update.

They're clearly building better training datasets and doing extensive RL on these benchmarks over time. The out of distribution performance is still awful.
Post reply on HN