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

GPT-5.6

openai.com

Post reply on HN
Print view View original

791–800 of 1001 posts

Re: GPT-5.6

#791

Post by roncesvalles »

ravenstine wrote: post #94
minimaxir wrote: post #26

The developer's guide ( https://developers.openai.com/api/docs/guides/latest-model ) has some interesting semantic tips for using the model: > Intent understanding: GPT-5.6 can better infer the user’s underlying goal and intended level of work without you specifying every step. Continue to state important constraints, approval boundaries, and success criteria explicitly. > Original image detail: GPT-5.6 preserves the…

> Avoid generic brevity instructions That part is confusing because it's not like they provide an example of how default GPT-5.6 output compares with GPT-5.5 both with default output and prompted for brevity. Whenever I use such prompts, it's usually because I want the model to give me the gist in a few sentences. I'd be stunned if GPT-5.6 was that concise by default. I would think that could "break" a lot of things…

I think it is widely known by now that instructions to alter the LLM's "tone", things like asking it to adopt a persona ("you are the world's best programmer"), and overly broad directives ("make no mistakes") always gives poor results. Just state directly what you want. If you want something very specific, add more information. "Prompt engineering" is pseudoscience.

To put it another way, you will only get the benchmarked performance if you let it talk the way it talks by default. Trying to modify this neuters the model's IQ.

Re: GPT-5.6

#792

Post by sneezychl »

mlmonkey wrote: post #738

Where is Gemini in all this? Lately it's not even been in the running. Sir Demis asleep at the wheel? Or Google too scared to release a SOTA model? Or ... maybe Gemini 4 is too good and the NSA is using it to break into systems worldwide ...?

I expect Google will drop a new SOTA model soon. Rumor has it they're training a new model from the ground-up, which takes a while.

Re: GPT-5.6

#793

Post by snthpy »

bevekspldnw wrote: post #331
10xDev wrote: post #234

Earlier quoted context omitted.

Seeing the dramatic differences in scores just going from high to xhigh is just another demonstration of the bitter lesson: Just keep scaling search and learning. We are probably going to need a lot more GPUs.

These aren’t raw base models they are the result of a ton of RLHF and various adjustments. Bitter lesson wildly overstated in this context.

Not just RLHF but also RLVR, and isn't that the litter lesson though?

My sense of the Sutton Dwarkesh interview was that he was calling out that he didn't mean just longer datasets, but rather learning through exploration and that's exactly RL.

Re: GPT-5.6

#794

Post by tw1984 »

joerawr wrote: post #744

I really appreciate the focus on intelligence WITH token efficiency. I'd like to see that become the trend. Smartest per token metrics. Least tokens to accomplish the task above a certain success level. Most of my tasks would benefit from efficiency / token, but switching models constantly, and trying to guess the right model and effort level takes up too much of my processing.

> I really appreciate the focus on intelligence WITH token efficiency

that is a polite way of saying "I don't believe AGI is coming anytime soon".

Re: GPT-5.6

#795

Post by senko »

zahlman wrote: post #659
senko wrote: post #439

I love testing the new models by asking them to code a toy RTS game. Here's what Terra did: https://senko.net/vibecode-bench/2026/rts-gpt-5.6-terra.html (one try, in codex app, xhigh effort) Comparing this to other models, I find it similar to GPT-5.5 and a bit behind Sonnet 5. You can see how other models fared here: https://senko.net/vibecode-bench/ (you can also fetch the prompt and the the 5.6 Terra resulting cod…

Could we see the prompts, though?

Here's the prompt I used:

> Create a simple but functional real time strategy (RTS) game similar to old WarCraft, StarCraft or Command & Conquer games. The player should be able to build buildings, create units, gather resources and should uncover the whole map. No AI or multiplayer needed. Use simple but nice-looking graphics. No sound. Implement everything in HTML/CSS/JS, everything in a single file (you can use 3rd-party js or css libraries/frameworks via CDN).

Re: GPT-5.6

#797

Post by romanhn »

wwind123 wrote: post #127
Syntaf wrote: post #6

Ok long time Claude Code user here; lately I've started to realize there's other great models out there I should be trying, but I'm hesitant to leave Claude Code behind for something new. What's the consensus today on codex vs claude code, does it really matter anymore?

I've been using Claude Code, Codex, Gemini (now Antigravity) at the same time for half year now, ever since I dipped my toe into agentic coding. I'd say in general Claude Code and Codex are equally powerful, Gemini is lagging behind. One thing I appreciate with Codex is, OpenAI nowadays sometimes just gives you quota resets you can bank, so when you use up weekly quota before the week ends, you could just reset the q…

The banked resets have been a game changer for me. I've been sticking to 5.4 medium mostly because 5.5 seemed to eat into my quota significantly faster. The reset bank gave me confidence to seriously start using 5.5 high. Lo and behold, I have yet to actually need a reset, but I'm now less likely to explore non-OpenAI models since there's an escape hatch with new models in case a coding session gets a bit crazy.

Re: GPT-5.6

#798

Post by rdtsc »

matheusmoreira wrote: post #626
midtake wrote: post #309

Earlier quoted context omitted.

You shouldn't know too much about biology, stupid human. You might live your life in an unexploitable way.

Anthropic's talk of "uplifting" people was so abhorent.

> Anthropic's talk of "uplifting" people was so abhorent.

Let’s be generous, it will uplift the investors pretty well once they start charging the real token costs and maybe drive out a few competitors.

Re: GPT-5.6

#799

Post by snthpy »

Syntaf wrote: post #6

Ok long time Claude Code user here; lately I've started to realize there's other great models out there I should be trying, but I'm hesitant to leave Claude Code behind for something new. What's the consensus today on codex vs claude code, does it really matter anymore?

OT but how are y'all sharing your skills and agents across harnesses?

I have a bunch of Claude Code Plugins and yesterday asked Codex to make them accessible to itself. It wanted to rewrite most of it. I was hoping i could get by with some symlinks or something to avoid drift.

Re: GPT-5.6

#800

Post by znnajdla »

tw1984 wrote: post #794
joerawr wrote: post #744

I really appreciate the focus on intelligence WITH token efficiency. I'd like to see that become the trend. Smartest per token metrics. Least tokens to accomplish the task above a certain success level. Most of my tasks would benefit from efficiency / token, but switching models constantly, and trying to guess the right model and effort level takes up too much of my processing.

> I really appreciate the focus on intelligence WITH token efficiency that is a polite way of saying "I don't believe AGI is coming anytime soon".

Not sure why you would think a focus on efficiency means less performance. Compression is intelligence. Higher efficiency enables higher performance.
Post reply on HN