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

GPT-5.3-Codex

openai.com

Post reply on HN
Print view View original

371–380 of 634 posts

Re: GPT-5.3-Codex

#371

Post by bcarv »

hyldmo wrote: post #359
bcarv wrote: post #356

Earlier quoted context omitted.

Does the AI agent know what your company is doing right now, what every coworker is working on, how they are doing it, and how your boss will change priorities next month without being told? If it really knows better, then fire everyone and let the agent take charge. lol

No, but Codex wouldn’t have asked you those questions either

For me, it still asks for confirmation at every decision when using plans. And when multiple unforeseen options appear, it asks again. I don’t think you’ve used Codex in a while.

Re: GPT-5.3-Codex

#372

Post by fluidcruft »

Rperry2174 wrote: post #211
utilize1808 wrote: post #202

Earlier quoted context omitted.

I think it's the opposite. Especially considering Codex started out as a web app that offers very little interactivity: you are supposed to drop a request and let it run automatously in a containerized environment; you can then follow up on it via chat --- no interactive code editing.

Fair I agree that was true of early codex and my perception too.. but today there are two announcements that came out and thats what im referring to. specifically, the GPT-5.3 post explicitly leans into "interactive collaborator" langauge and steering mid execution OpenAI post: "Much like a colleague, you can steer and interact with GPT-5.3-Codex while it’s working, without losing context." OpenAI post: "Instead of w…

Frankly it seems to be that codex is playing catch-up with claude code and claude code is just continuing to move further ahead. The thing with claude code is it will work longer... if you want it to. It's always had good oversight and (at least for me) it builds trust slowly until you are wishing it would do more at once. When I've used codex (it has been getting better) but back in the day it would just do things and say it's done and you're just sitting there wondering "wtf are you doing?". Claude code is more the opposite where you can watch as closely as you want and often you get to a point where you have enough trust and experience with it that you know what it's going to do and don't want to bother.

Re: GPT-5.3-Codex

#373

Post by AstroBen »

RivieraKid wrote: post #284

Do software engineers here feel threatened by this? I certainly am. I'm surprised that this topic is almost entirely missing in these threads.

No. It turns into a complete mess without someone that knows what they're doing to steer it. It's an upgrade to autocomplete

Re: GPT-5.3-Codex

#374

Post by zeroxfe »

_zoltan_ wrote: post #297
ghosty141 wrote: post #228

Earlier quoted context omitted.

I'm personally 100% convinced (assuming prices stay reasonable) that the Codex approach is here to stay. Having a human in the loop eliminates all the problems that LLMs have and continously reviewing small'ish chunks of code works really well from my experience. It saves so much time having Codex do all the plumbing so you can focus on the actual "core" part of a feature. LLMs still (and I doubt that changes) can't…

I'm personally 100% convinced of the opposite, that it's a waste of time to steer them. we know now that agentic loops can converge given the proper framing and self-reflectiveness tools.

> it's a waste of time to steer them

It's not a waste of time, it's a responsibility. All things need steering, even humans -- there's only so much precision that can be extrapolated from prompts, and as the tasks get bigger, small deviations can turn into very large mistakes.

There's a balance to strike between micro-management and no steering at all.

Re: GPT-5.3-Codex

#375

Post by mmaunder »

Take a screenshot of ARG-AGI-2 leaderboard now because GPT-5.3-Codex isn't up there yet and I suspect it'll cram down Claude Opus 4.6 which rules the roost for the next few hours. King for a day.

Re: GPT-5.3-Codex

#376

Post by mmaunder »

the_duke wrote: post #19
granzymes wrote: post #3

I think Anthropic rushed out the release before 10am this morning to avoid having to put in comparisons to GPT-5.3-codex! The new Opus 4.6 scores 65.4 on Terminal-Bench 2.0, up from 64.7 from GPT-5.2-codex. GPT-5.3-codex scores 77.3.

I do not trust the AI benchmarks much, they often do not line up with my experience. That said ... I do think Codex 5.2 was the best coding model for more complex tasks, albeit quite slow. So very much looking forward to trying out 5.3.

ARG-AGI-2 leaderboard has a strong correlation with my Rust/CUDA coding experience with the models.

Re: GPT-5.3-Codex

#377

Post by JackYoustra »

codethief wrote: post #279
itay-maman wrote: post #102

Something that caught my eye from the announcement: > GPT‑5.3‑Codex is our first model that was instrumental in creating itself. The Codex team used early versions to debug its own training I'm happy to see the Codex team moving to this kind of dogfooding. I think this was critical for Claude Code to achieve its momentum.

Sounds like the researchers behind https://ai-2027.com/ haven't been too far off so far.

> researchers

that's certainly one way to refer to Scott Alexander

Re: GPT-5.3-Codex

#378

Post by mmaunder »

kilroy123 wrote: post #111
NitpickLawyer wrote: post #34

Earlier quoted context omitted.

Just some anecdata++ here but I found 5.2 to be really good at code review. So I can have something crunched by cheaper models, reviewed async by codex and then re-prompt with the findings from the review. It finds good things, doesn't flag nits (if prompted not to) and the overall flow is worth it for me. Speed loss doesn't impact this flow that much.

Personally, I have Claude do the coding. Then 5.2-high do the reviewing.

I might flip that given how hard it's been for Claude to deal with longer context tasks like a coding session with iterations vs a single top down diff review.

Re: GPT-5.3-Codex

#379

Post by pcloadlett3r »

ifwinterco wrote: post #342
legulere wrote: post #273

Earlier quoted context omitted.

I don't think that the user you are responding to is anti-innovation, but rather points out that the usefulness of AI is oversold. I'm using Copilot for Visual Studio at work. It is useful for me to speed some typing up using the auto-complete. On the other hand in agentic mode it fails to follow simple basic orders, and needs hand-holding to run. This might not be the most bleeding-edge setup, but the discrepancy be…

I think copilot is widely considered to be fairly rubbish, your description of agentic coding was also my experience prior to ~Q3 2025, but things have shifted meaningfully since then

Copilot has access to the latest models like Opus 4.6 in agentic mode as well. It's got certain quirks and I prefer a TUI myself but it isn't radically different.

Re: GPT-5.3-Codex

#380

Post by audience_mem »

nubg wrote: post #223
nerdsniper wrote: post #160

Earlier quoted context omitted.

Opus 4.5 still worked better for most of my work, which is generally "weird stuff". A lot of my programming involves concepts that are a bit brain-melting for LLMs, because multiple "99% of the time, assumption X is correct" are reversed for my project. I think Opus does better at not falling into those traps. Excited to try out 5.3

what do you do?

He works on brain-melting stuff, the understanding of which is far beyond us.
Post reply on HN