GPT-5.3-Codex • Hacker News Board

Re: GPT-5.3-Codex

#101

Post by roya51788 » Thu, Feb 05, 2026, 6:56 PM UTC

what are the benchmarks against opus 4.6?

Re: GPT-5.3-Codex

#102

Post by itay-maman » Thu, Feb 05, 2026, 6:56 PM UTC

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.

Re: GPT-5.3-Codex

#103

Post by alexhans » Thu, Feb 05, 2026, 6:56 PM UTC

modeless wrote: post #41

It's so difficult to compare these models because they're not running the same set of evals. I think literally the only eval variant that was reported for both Opus 4.6 and GPT-5.3-Codex is Terminal-Bench 2.0, with Opus 4.6 at 65.4% and GPT-5.3-Codex at 77.3%. None of the other evals were identical, so the numbers for them are not comparable.

Isn't the best eval the one you build yourself, for your own use cases and value production?

I encourage people to try. You can even timebox it and come up with some simple things that might look initially insufficient but that discomfort is actually a sign that there's something there. Very similar to moving from not having unit/integration tests for design or regression and starting to have them.

Re: GPT-5.3-Codex

#104

Post by InsideOutSanta » Thu, Feb 05, 2026, 6:57 PM UTC

edem wrote: post #23

So can I use this from Opencode? Because Anthropic started to enforce their TOS to kill the Opencode integration

Yes, OpenAI said they'd allow usage of their subscriptions in opencode.

Re: GPT-5.3-Codex

#105

Post by ponyous » Thu, Feb 05, 2026, 6:57 PM UTC

I think models are smart enough for most of the stuff, these little incremental changes barely matter now. What I want is the model that is fast.

Re: GPT-5.3-Codex

#106

Post by hubraumhugo » Thu, Feb 05, 2026, 6:57 PM UTC

Anybody else not seeing it available in Codex app or CLI yet (with Plus)?

Re: GPT-5.3-Codex

#107

Post by trilogic » Thu, Feb 05, 2026, 6:58 PM UTC

wasmainiac wrote: post #61

raincole wrote: post #33

Earlier quoted context omitted.

AI fried brains, unfortunately.

I mean, he has a point it’s just not very eloquently written.

I empathize with the situation, no elegance from them, no eloquence from me :)

Re: GPT-5.3-Codex

#108

Post by regularfry » Thu, Feb 05, 2026, 6:59 PM UTC

edem wrote: post #23

So can I use this from Opencode? Because Anthropic started to enforce their TOS to kill the Opencode integration

I've tried opus 4.5 in opencode via the GitHub Copilot API, mostly to see if it works all. I don't think that broke any terms of service? But also I haven't checked how much more expensive I made it for myself over just calling them directly.

Re: GPT-5.3-Codex

#109

Post by superze » Thu, Feb 05, 2026, 7:01 PM UTC

sdf2erf wrote: post #57

trilogic wrote: post #22

When 2 multi billion giants advertise same day, it is not competition but rather a sign of struggle and survival. With all the power of the "best artificial intelligence" at your disposition, and a lot of capital also all the brilliant minds, THIS IS WHAT YOU COULD COME UP WITH? Interesting

Yeah they are both fighting for survival. No surprise really. Need to keep the hype going if they are both IPO'ing later this year.

How many IPOs can a company really do?

Re: GPT-5.3-Codex

#110

Post by kopollo » Thu, Feb 05, 2026, 7:01 PM UTC

Where is the google?