Live data from Hacker News

GPT-5.3-Codex

openai.com

591–600 of 634 posts

Re: GPT-5.3-Codex

#591
post #432

Earlier quoted context omitted.

I'm building all of the systems with LLMs and using LLMs to fast track the creation of content such as storylines, characters, etc. All of the assets are mostly bought and created by me.

Sounds fun! Asset creation...at least in terms of story content, should be the one area where LLMs would really shine, especially if it can somehow extend into logic and gameplay. Couple that with the ways of generating art assets (hard with an LLM, but it can do something at least), that would be cool. I hope to see these games in the future, although they might be labelled as slop unless done really well.

Actually, LLM fiction writing is awfully bad. But it does help with ideas!

I'm trying my hardest to make it feel high quality instead of just slop.

Re: GPT-5.3-Codex

#592
post #408
post #136

I'm having a hard time parsing the openai website. Anyone know if it is possible to use this model with opencode with the plus subscription?

It's possible to use opencode with the plus subscription using this plugin for auth [0][1]. Just tested this and it appears to work. [0]: https://opencode.ai/docs/ecosystem/#:~:text=Use%20your%20Cha... [1]: https://github.com/numman-ali/opencode-openai-codex-auth

You do not need a plugin anymore.

Re: GPT-5.3-Codex

#594

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.

Is gpt5.3 200x bigger than gpt4? Looks like openai used this fanfiction as its marketing strategy

Re: GPT-5.3-Codex

#595

Earlier quoted context omitted.

I just asked Opus 4.6 to debug a bug in my current changes and it went for 20 minutes before I interrupted it. Take that as you will.

Doesn't feel like a useful data point without more context. For some hard bugs I'd be thrilled to wait 30 minutes for a fix, for a trivial CSS fix not so much. I've spent weeks+ of my career fix single bugs. Context is everything.

> I've spent weeks+ of my career fix single bugs.

Same, same. It's not a useful data point at all.

bug: llm alignment

timeframe to fix : probably never

Re: GPT-5.3-Codex

#596
post #206

Earlier quoted context omitted.

I've also had the exact opposite experience with tone. Claude Code wants to build with me, and Codex wants to go off on its own for a while before returning with opinions.

In terms of 'tone', I have been very impressed with Qwen-code-next over the last 2 days, especially as I have it running locally on a single modest 4090.

Did you set that up following a guide or anything you could share?

Re: GPT-5.3-Codex

#597

Earlier quoted context omitted.

In terms of 'tone', I have been very impressed with Qwen-code-next over the last 2 days, especially as I have it running locally on a single modest 4090.

Did you set that up following a guide or anything you could share?

not OP, but I got it running on my 4090 (and RAM) by following this guide: https://unsloth.ai/docs/models/qwen3-coder-next

I see around 30 t/s

Re: GPT-5.3-Codex

#598

Earlier quoted context omitted.

In terms of 'tone', I have been very impressed with Qwen-code-next over the last 2 days, especially as I have it running locally on a single modest 4090.

Did you set that up following a guide or anything you could share?

Easiest way I know is to just use LMStudio. Just download and press play :). Optional, but recommended, increase the context length to 262144 if you have the DRAM available. It will definitely get slower as your interaction prolongs, but (at least for me) still tolerable speed.

Re: GPT-5.3-Codex

#599

Earlier quoted context omitted.

Google Gemini definitely has structured output.

Not so fast! Check this out https://github.com/googleapis/python-genai/issues/460 In my experience, you can only use Gemini structured outputs for the most trivial of schemas. No integer literals, no discriminated unions and many more paper cuts. So at least for me, it was completely unusable for what I do at work.

That's the level of coding I expect from a bunch of Python-only ML computer scientists, but still... wow.

On the upside, they seem to have fixed it: https://blog.google/innovation-and-ai/technology/developers-...

Re: GPT-5.3-Codex

#600

I remember when AI labs coordinated so they didn't push major announcements on the same day to avoid cannibalizing each other. Now we have AI labs pushing major announcements within 30 minutes .

The labs have fully embraced the cutthroat competition, the arms race has fully shed the civilized facade of beneficient mutual cooperation. Dirty tricks and underhanded tactics will happen - I think Demis isn't savvy in this domain, but might end up stomping out the competition on pure performance. Elon, Sam, and Dario know how to fight ugly and do the nasty political boardroom crap. 26 is gonna be a very dramatic y…

demis is more than qualified. he was politically savvy enough to stay in control of deepmind when it was acquired by google, thats up there with the altman fiasco a year or two ago.
Post reply on HN