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

631–640 of 1001 posts

Re: GPT-5.6

#631

Post by matheusmoreira »

cmrdporcupine wrote: post #385
revolvingthrow wrote: post #376

Benchmarks look really promising. Suspiciously good, even. I guess we’ll see soon enough. My question to previewers: how are the guardrails for random joe that wasn’t personally blessed by the ai pope to access the non-nerfed model? Fable is a nightmare in this regard, but I’m not sure whether 5.6 also gets a critical side-eye from the gubmint when you ask it to fix bugs in your code (you filthy hacker, you).

I almost immediately ran into "This request requires additional safety checks, which can take extra time. Hang tight or retry with a faster model for a quicker response, though it may be less capable of handling complex requests." Which is something I've never seen with codex before, and I wasn't doing anything funky. Just writing CUDA kernels and benchmarks for them.

Is it actually usable though? Because the Fable situation is just obnoxious. If OpenAI's Fable equivalent is actually usable, I'll cancel my Anthropic subscription on the spot.

Re: GPT-5.6

#632

Post by XCSme »

Jcampuzano2 wrote: post #152

I really wish there was just an easy guide on when to use Sol vs Terra vs Luna, and it just moves further into confusing territory when it comes to naming. The naming convention is especially difficult to decipher depending on what your native language is. Of course a latin language speaker might be able to easily determine oh yeah each one is slightly bigger than the other but I still think it borderlines too confus…

In my tests, in almost all cases, using Sol on (low) reasoning is the best option intelligence/price-wise.

Luna is good too, for classification tasks or any pre-processing task that is not critical

Re: GPT-5.6

#634

Post by user43928 »

ftchd wrote: post #284
aliasxneo wrote: post #186

"We've extended usage of Claude Fable" message incoming any day now.

They reset all usage half an hour ago. It's back to 0% per week and session. No specifically Fable related.

I let it work on two features while I was using mostly GPT 5.6 and it has already consumed 10% of the weekly Fable limit on Max x20.

GPT 5.6 on the Pro x5 plan is down to... 100%. It looks like they just reset the usage limits again. And I still have two resets on the bench.

Anthropic is going to have to up their game to compete.

Re: GPT-5.6

#635

Post by zahlman »

egorfine wrote: post #402
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…

> Intent understanding This will totally make it brain damaged over a certain tasks. Sort of like the same brain damage that prompted OpenAI project managers to destroy ChatGPT.app today.

> destroy ChatGPT.app today.

... What changed, exactly?

Re: GPT-5.6

#637

Post by lavela »

small_model wrote: post #616
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?

Now we have various Opus+ level models (Opus/Fable, Grok 4.5, GPT 5.6) I prefer to focus on price/speed and harness as models are all generally good enough for coding. (Fable is overkill for 90% of work but is still level above). So I use Grok Build with 4.5 as its VERY fast and cheap, Codex is next best for me with sol/lunar 5.6. and Claude Code Fable for the 10% of tasks that need that level of reasoning. However I…

Am I missing something or isn't sol/lunar 5.6 only out for like 3 hours? How did you evaluate?

Re: GPT-5.6

#638

Post by matheusmoreira »

danielbln wrote: post #335
sd9 wrote: post #17

I haven't tried an OpenAI model for a long time, but with Fable going to API pricing soon this might be enough to get me to try codex.

Seeing how Anthropomorphic just reset usage quotas back to 0 and the other day extended Fable sub inclusion by a few days, I have a feeling they might not drop Fable out of sub after all, because like you I would most definitely take a long good look at codex at that point.

It's not just the API pricing either, there's also the constant uncertainty. They pull the model then put it back up, they say the model is going away then suddenly it's not. And then there's the fact Fable is barely usable because it randomly downgrades to Opus out of nowhere whenever it thinks about exploits.

It's definitely good that Anthropic's feeling the pressure. Anthropic has worn out their welcome with this "safety" nonsense. If OpenAI actually lets me use the LLMs on a subscription without any of this bullshit, I'll definitely switch.

Re: GPT-5.6

#640

Post by cmrdporcupine »

matheusmoreira wrote: post #631
cmrdporcupine wrote: post #385

Earlier quoted context omitted.

I almost immediately ran into "This request requires additional safety checks, which can take extra time. Hang tight or retry with a faster model for a quicker response, though it may be less capable of handling complex requests." Which is something I've never seen with codex before, and I wasn't doing anything funky. Just writing CUDA kernels and benchmarks for them.

Is it actually usable though? Because the Fable situation is just obnoxious. If OpenAI's Fable equivalent is actually usable, I'll cancel my Anthropic subscription on the spot.

Yes it's usable, however it does make it difficult to just do /goal and walk away if this is happening periodically. I don't do that often, but for well defined things I sometimes do.
Post reply on HN