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

GPT‑5.3‑Codex‑Spark

openai.com

Post reply on HN
Print view View original

181–190 of 415 posts

Re: GPT‑5.3‑Codex‑Spark

#181

Post by zem »

nikkwong wrote: post #64
gamegoblin wrote: post #38

Earlier quoted context omitted.

I routinely leave codex running for a few hours overnight to debug stuff If you have a deterministic unit test that can reproduce the bug through your app front door, but you have no idea how the bug is actually happening, having a coding agent just grind through the slog of sticking debug prints everywhere, testing hypotheses, etc — it's an ideal usecase

I have a hard time understanding how that would work — for me, I typically interface with coding agents through cursor. The flow is like this: ask it something -> it works for a min or two -> I have to verify and fix by asking it again; etc. until we're at a happy place with the code. How do you get it to stop from going down a bad path and never pulling itself out of it? The important role for me, as a SWE, in the p…

it's more like "this function is crashing with an inconsistent file format error. can you figure out how a file with the wrong format got this far into the pipeline?". in cases like that the fix is usually pretty easy once you have the one code path out of several thousands nailed down.

Re: GPT‑5.3‑Codex‑Spark

#182

Post by mbm »

Works pretty well as a general-purpose computer. The speed is really enjoyable. Could replace some of my Claude Code use actually. For coding, set to xhigh and use it for personal tools or small projects.

Example repo that Codex with spark made in about 15 minutes for me since `claude --resume` has been finicky lately: https://github.com/mzxrai/claude-sessions

Re: GPT‑5.3‑Codex‑Spark

#184

Post by girvo »

seunosewa wrote: post #120
johnfn wrote: post #76

Earlier quoted context omitted.

The other day I got Codex to one-shot an upgrade to Vite 8 at my day job (a real website with revenue). It worked in this for over 3 hours without intervention (I went to sleep). This is now in production.

How did you verify it?

Just send it bro

(but honestly for a lot of websites and web apps you really can just send it, the stakes are very low for a lot of what most people do, if they're honest with themselves)

Re: GPT‑5.3‑Codex‑Spark

#185

Post by bsharper »

crystal_revenge wrote: post #179
clickety_clack wrote: post #117

Earlier quoted context omitted.

It would be so cool if it generated live in the presentation and adjusted live as you spoke, so you’d have to react to whatever popped on screen!

There was a pre-LLM version of this called "battledecks" or "PowerPoint Karaoke"[0] where a presenter is given a deck of slides they've never seen and have to present on it. With a group of good public speakers it can be loads of fun (and really impressive the degree that some people can pull it off!) 0. https://en.wikipedia.org/wiki/PowerPoint_karaoke

There is a Jackbox game called "Talking Points" that's like this: the players come up with random ideas for presentations, your "assistant" (one of the other players) picks what's on each slide while you present: https://www.youtube.com/watch?v=gKnprQpQONw

Re: GPT‑5.3‑Codex‑Spark

#186

Post by joshuastuden »

behnamoh wrote: post #18
cjbarber wrote: post #16

Earlier quoted context omitted.

> In my opinion, they solved the wrong problem. The main issue I have with Codex is that the best model is insanely slow, except at nights and weekends when Silicon Valley goes to bed. I don't want a faster, smaller model (already have that with GLM and MiniMax). I want a faster, better model (at least as fast as Opus). It's entirely possible that this is the first step and that they will also do faster better models…

I doubt it; there's a limit on model size that can be supported by Cerebras tech. GPT-5.3 is supposedly +1T parameters...

Um, no. There's no limit on model size for Cerebras hardware. Where do you come up with this stuff?

Re: GPT‑5.3‑Codex‑Spark

#187

Post by 2001zhaozhao »

raahelb wrote: post #144

Interesting to note that the reduced latency is not just due to the improved model speed, but also because of improvements made to the harness itself: > "As we trained Codex-Spark, it became apparent that model speed was just part of the equation for real-time collaboration—we also needed to reduce latency across the full request-response pipeline. We implemented end-to-end latency improvements in our harness that wi…

This might actually be hard for open source agents (e.g. Opencode) to replicate, barring a standardized WebSocket LLM API being widely adopted.

Re: GPT‑5.3‑Codex‑Spark

#189

Post by sam_goody »

perdomon wrote: post #183

This has been the industry standard for the last 20 minutes. I can't believe people are still using GPT-5.3-Codex.

I read this headline and was like, "A look, an announcement by GPT!! That means that Google or Anthropic must have had a release today!"

And, yup, there is Gemini in item 3!

Re: GPT‑5.3‑Codex‑Spark

#190

Post by ghosty141 »

mickeyp wrote: post #22
antirez wrote: post #20

The search for speed is vain. Often Claude Code Opus 4.6, on hard enough problems, can do the impression of acting fast without really making progresses because of lack of focus on what matters. Then you spin the much slower GPT 5.3-Codex and it fixes everything in 3 minutes of doing the right thing.

I disagree. This is great for bulk tasks: renaming, finding and searching for things, etc

What codex often does for this, write a small python script and execute that to bulk rename for example.

I agree that there is use for fast "simpler" models, there are many tasks where the regular codex-5.3 is not necessary but I think it's rarely worth the extra friction of switching from regular 5.3 to 5.3-spark.

Post reply on HN