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

561–570 of 1001 posts

Re: GPT-5.6

#561

Post by loufe »

swatcoder wrote: post #336
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…

> can better infer the user’s underlying goal and intended level of work This is a trap. It's the optimistic fallacy that poisons all "consumer scale" machine learning products and what's going to effectively ruin these models as they keep chasing it in the same way that web queries were ruined, social media feeds were ruined, and media recommenders were ruined. For the vendor, optimizing metrics across their whole u…

I agree to an extent but it needs to be balanced. Receiving a half-baked, extremely verbose recap of thinking on benign details with Opus 4.8 or GPT 5.5 feels like an extraordinary loss of quality of experience compared with fable 5.

Yes it shares less, but I think the trade-off is you pay less in tokens and hopefully it's truly just not needing to say things because it truly does just better get what you're saying, think to read X markdown file or GH issue which contains the info, etc.

As long as I can still push back and get it to share its thinking on demand and I'm confident the model isn't actually basing things on poor premises, this is okay for me. I am more productive when not inundated with time-wasting check-ins.

That said, I absolutely lament the loss of the ability to access the thinking - I would happily read the "DANGER DANGER DANGER" internal gremlin thoughts fable 5 makes to verify something if they were accessed, and prefer that to a recap presented only for my benefit.

Re: GPT-5.6

#562

Post by fblp »

eig wrote: post #38

Funny to see that they did not include Fable 5 in their GeneBench and LifeSciBench comparisons because "it does not answer advanced biology questions and refuses the majority of questions in this eval". Winner by default!

oh that's sad, are the biolgy limitations for "safety"?

Re: GPT-5.6

#563

Post by HarHarVeryFunny »

user43928 wrote: post #507
HarHarVeryFunny wrote: post #467

Not specific to OpenAI / Codex, but I'm curious what people are doing to protect themselves from any destructive actions by their coding agents? Just install and pray? Explicity approve all actions? Reconfigure for safety? Run in a sandbox (Docker) ?

I use the auto-reviewer for actions outside the builtin sandbox. So far this has been rock solid, and tens of millions of developers use this setup without issue. It is not going to wipe our hard disks. At least I hope so. Fable and GPT 5.6 have been ever more proactive, and GPT 5.6 is automating the AppStore on my machine to download an Xcode update while I am typing this.

Is this auto-reviewer part of Codex? Is the review done by the agent or the model?

Re: GPT-5.6

#565

Post by kordlessagain »

paxys wrote: post #194
philip1209 wrote: post #102

Will this run on Cerebas? I'm really looking forward to that.

Sam Altman confirmed during the initial limited release that Sol will run on Cerebras at 750 tok/sec.

"I canna' give her any more, Captain!" - Montgomery "Scotty" Scott, Chief Engineer

Re: GPT-5.6

#566

Post by fellowniusmonk »

inciampati wrote: post #118
eig wrote: post #38

Funny to see that they did not include Fable 5 in their GeneBench and LifeSciBench comparisons because "it does not answer advanced biology questions and refuses the majority of questions in this eval". Winner by default!

This is a major reason why I and a number of biologists I've talked to have canceled their anthropic accounts recently. Not working is not working.

I mean it's a fucking joke, I kept getting refusals on a code base I wasn't familiar with and it was literally just because there are some vars named DNA. Just absolutely stupid.

Re: GPT-5.6

#567

Post by kordlessagain »

__mharrison__ wrote: post #549
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…

Serious question: what is a short prompt? (For that matter at what point is it "long"? And does the rest of the context matter? Should it be short too?)

"fix this shit"

Re: GPT-5.6

#568

Post by bsenftner »

__mharrison__ wrote: post #549
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…

Serious question: what is a short prompt? (For that matter at what point is it "long"? And does the rest of the context matter? Should it be short too?)

It creates the context of the request without including language or terms that activate additional areas of knowledge not necessary for an accurate reply.

Re: GPT-5.6

#570

Post by user43928 »

HarHarVeryFunny wrote: post #563
user43928 wrote: post #507

Earlier quoted context omitted.

I use the auto-reviewer for actions outside the builtin sandbox. So far this has been rock solid, and tens of millions of developers use this setup without issue. It is not going to wipe our hard disks. At least I hope so. Fable and GPT 5.6 have been ever more proactive, and GPT 5.6 is automating the AppStore on my machine to download an Xcode update while I am typing this.

Is this auto-reviewer part of Codex? Is the review done by the agent or the model?

Yes. In Codex it is called 'Approve for me', in Claude it is 'Auto mode'.

I believe in both cases it is prompting a model with a fresh context that is tasked with reviewing the reason for the action.

With Claude, I have seen that if the reviewer does reject the proposed action, it responds with a long text about how the Agent should not try to work around this rejection, and instead prompt the user for an explicit approval of the proposed action.

Post reply on HN