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

771–780 of 1001 posts

Re: GPT-5.6

#771

Post by theptip »

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.

Nah, the last few generations have more RLVR in the data mix. Which is more CPU intensive and very much amenable to the bitter lesson as you can reduce the loss by doing more rollouts in your tool environment.

Re: GPT-5.6

#773

Post by chaos_emergent »

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.

RLHF is an increasingly small part of training though? From what I understand most of the capability gain is in RLVR

Re: GPT-5.6

#774

Post by CyberDildonics »

Maxatar wrote: post #337
simianwords wrote: post #218

Earlier quoted context omitted.

Very interesting. My prediction is that Mythos would outperform Sol. Also what does this tell about Yann LeCuns whole world model theory? Bro has been going on and on about it. He has made multiple wrong predictions on the trajectory of LLMs. At some point his claim should be fully falsified no?

Falsifying Yann Lecun isn't exactly a priority for anyone seriously working in this space.

What is this supposed to mean?

Re: GPT-5.6

#775

Post by varenc »

apinstein wrote: post #688
zahlman wrote: post #635

Earlier quoted context omitted.

> destroy ChatGPT.app today. ... What changed, exactly?

Codex.app is gone and merged into ChatGPT.app. The upgrade process was... messy... Codex's self-update just deleted the Codex.app w/o further instruction. And ChatGPT updater failed the first time while also bricking the prior installed ChatGPT.app. Seems good/fine once you get through upgrading the app.

Wow, stories like this make me happy that I block all ChatGPT/Claude/Codex/etc updates by default, and only selectively update on demand. I do this just by setting a network rule that blocks their update check. (fortunately updates are still served on a different domain than regular usage)

Re: GPT-5.6

#776

Post by derpified »

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

Does this mean ChatGPT will stop botsplaining things to me? I get it quite a bit more per unit time from ChatGPT than claude. Maybe that will change now.

(By botsplaining I mean when the AI explains some unstated premise of the prompt itself back at me as a correction when in many cases it's the motivation for the question in the first place)

Re: GPT-5.6

#777

Post by Culonavirus »

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) ?

YOLO.

Btw for real tho, if you don't have the time or means to mess with full sandboxed environments, just working within a git repo and instructing on your agents.md project level that the agent should back up dirty files (local changes that were not yet committed) before changing them is enough and super fast and easy to set up. And by back up I just mean a simple instruction to back up to some temp location under random named, but rembered during one "turn" of agent thinking, subfolder ( .../temp/{random}/orginal/tree/file.xyz )

This is so the agent (or you later) can recover even locally changed files if it messes them up for whatever reason.

As for the rest you gotta watch what you're asking for, but generally speaking, these SOTA models are smart, none of them will just delete your stuff even with full access. I've been raw dogging multiple projects on my work machine with zero issues of this kind for months. I created codex_reader read only acccounts for my local databases and just add that to agents.md with a note its allowed to only use that and never had a problem.

Re: GPT-5.6

#778

Post by jeffybefffy519 »

derpified wrote: post #776
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 Does this mean ChatGPT will stop botsplaining things to me? I get it quite a bit more per unit time from ChatGPT than claude. Maybe that will change now. (By botsplaining I mean when the AI explains some unstated premise of the prompt itself back at me as a correction when in many cases it's the motivation for the question in the first place)

I found changing chatgpt's persona settings helped a lot with this!

Re: GPT-5.6

#779

Post by pkulak »

JohnBooty wrote: post #745
ryan_n wrote: post #474

Earlier quoted context omitted.

Genuine question/not a critique-are you actually reviewing all that code or just sending it and hoping for the best? I just can't imagine someone is reading/reviewing that much code every day, but maybe I'm wrong?

Not parent poster but: I probably spend at least 2/3 of my tokens on code review & QA. At least at my workplace, that's the culture.

Same. AI has found so many bugs I would have shipped a year ago.

Re: GPT-5.6

#780

Post by jeffybefffy519 »

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?

IMO Codex has been the same rollercoaster ride as Claude. GPT 5.3-codex was incredible for backend/system tasks, GPT5.5 is better all rounder but weaker in some spots. There has also been many weeks when Codex's models were dumb AF. Same rollercoaster ride as anthropic between Opus 4.5 to 4.8...

IMO the two biggest problems not really being answered by both OpenAI and Anthropic are: 1. Why not make specific models good at specific tasks for Codex/Claude Code. Theres a handful of types of work here whereby small good quality models would do better than these generalised all purpose models whereby someone discovers Fable is bad at biology.... 2. Why cant they consistently run these models and keep them performing? Performance of the models seems to directly correlate with amount of compute available, but they dont talk about it...

Post reply on HN