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

481–490 of 634 posts

Re: GPT-5.3-Codex

#481

Post by theLiminator »

dudeinhawaii wrote: post #182
wilg wrote: post #144

Earlier quoted context omitted.

In my personal experience the GPT models have always been significantly better than the Claude models for agentic coding, I’m baffled why people think Claude has the edge on programming.

I think for many/most programmers = 'speed + output' and webdev == "great coding". Not throwing shade anyone's way. I actually do prefer Claude for webdev (even if it does cringe things like generate custom CSS on every page) -- because I hate webdev and Claude designs are always better looking. But the meat of my code is backend and "hard" and for that Codex is always better, not even a competition. In that domain,…

Actually for me the killer feature isn't Claude, but is the planning mode.

It's a very nice UX for iteratively creating a spec that I can refine.

Re: GPT-5.3-Codex

#482

Post by rapind »

jaggederest wrote: post #452
rapind wrote: post #409

Earlier quoted context omitted.

Maybe some day, but as a claude code user it makes enough pretty serious screw ups, even with a very clearly defined plan, that I review everything it produces. You might be able to get away without the review step for a bit, but eventually (and not long) you will be bitten.

I use that to feed back into my spec development and prompting and CI harnesses, not steering in real time. Every mistake is a chance to fix the system so that mistake is less likely or impossible. I rarely fix anything in real time - you review, see issues, fix them in the spec, reset the branch back to zero and try again. Generally, the spec is the part I develop interactively, and then set it loose to go crazy. Th…

I assumed you'd build such a massive set of rules (that claude often does not obey) that you'd eat up your context very quickly. I've actually removed all plugins / MCPs because they chewed up way too much context.

Re: GPT-5.3-Codex

#483

Post by newtwilly »

ponyous wrote: post #105

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 .

I've been using 5.1-codex-max with low reasoning (in Cursor fwiw) recently and it feels like a nice speed while still being effective. Might be worth a shot.

Re: GPT-5.3-Codex

#484

Post by xvector »

lurking_swe wrote: post #435
energy123 wrote: post #418

Earlier quoted context omitted.

Unless you're retiring in less than 5 years this is extremely short sighted.

It’s also silly to try predicting the future 5 years from now, IMO. Historically progress is very unpredictable. It often plateaus when you least expect it. It’s good to be cautious and not in denial, but i usually ignore people who talk so authoritatively about the future. It’s just a waste of time. Everyone thinks they are right. My recommendation is have a very generous emergency fund and do your best to be effect…

Or just move into technical leadership or management/executive permissions.

In any case, everyone should be riding the AI wave! Anyone doing so should have enough to retire five years from now.

Re: GPT-5.3-Codex

#485

Post by Rapzid »

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

You are so behind the curve if you think copilot is mostly rubbish. That's a 4+ month old take.

Re: GPT-5.3-Codex

#486

Post by xvector »

nananana9 wrote: post #173

I've been listening to the insane 100x productivity gains you all are getting with AI and "this new crazy model is a real game changer" for a few years now, I think it's about time I asked: Can you guys point me ton a single useful, majority LLM-written, preferably reliable, program that solves a non-trivial problem that hasn't been solved before a bunch of times in publicly available code?

I work for a big tech company, most of our code today is written by agents. This includes backend infra and frontend app/UX code.

It satisfies your relevant criteria: LLM-written, reliable, non-trivial.

No major program is perfectly reliable so I wouldn't call it that (but we have fewer incidents vs human-written code), and "useful" is up to the reader (but our code is certainly useful to us.)

Re: GPT-5.3-Codex

#487

Post by speedgoose »

bryanhogan wrote: post #425
speedgoose wrote: post #154

Earlier quoted context omitted.

Today is the best day to rewrite everything in React. You may not enjoy React, but AI agents do. And they are the ones writing the code.

But human and AI agents enjoy writing Svelte even more. This really is a non-argument.

I don’t know, you ask above whether it can do svelte now.

Re: GPT-5.3-Codex

#488

Post by xvector »

revahage wrote: post #253
nananana9 wrote: post #173

I've been listening to the insane 100x productivity gains you all are getting with AI and "this new crazy model is a real game changer" for a few years now, I think it's about time I asked: Can you guys point me ton a single useful, majority LLM-written, preferably reliable, program that solves a non-trivial problem that hasn't been solved before a bunch of times in publicly available code?

Well, it took opus 4.5 five messages to solve a trivial git problem for me. It hallucinated nonexistent flags three times. Hallucinating nonexistent flags is certainly a novel solution to my git ineptness. Not to be outdone, chatgpt 5.2 thinking high only needed about 8 iterations to get a mostly-working ffmpeg conversion script for bash. It took another 5 messages to translate it to run in windows, on powershell (mo…

You've got to be doing something wrong IMO. Mind sharing your system prompt and prompt/response pairs?

Re: GPT-5.3-Codex

#489

Post by xvector »

falloutx wrote: post #320
avaer wrote: post #314

Earlier quoted context omitted.

I wish I could agree with you, but as a game dev, shader author, and occasional asm hacker, I still think AIs have demonstrated being perfectly capable of copying "those effects". It's been trained on them, of course. You're not gonna one-shot RD2, but neither will a human. You can one-shot particles and shader passes though.

I didnt say one shot it, coding agents have been out for more than couple years and yet we cant point to single Good piece of software built by it.

"Good" is obviously subjective but this mentality is so interesting because at my big tech company most of our software today is written by agents.

From my perspective, comments like these read as people having their head stuck in the sand (no offense, I might be missing something.)

Re: GPT-5.3-Codex

#490

Post by nitroedge »

readyforbrunch wrote: post #303
StephenHerlihyy wrote: post #167

Earlier quoted context omitted.

I don’t use OpenAI too much, but I follow a similar work flow. Use Opus for design/architecture work. Move it to Sonnet for implementation and build out. Then finally over to Gemini for review, QC and standards check. There is an absolute gain in using different models. Each has their own style and way of solving the problem just like a human team. It’s kind of awesome and crazy and a bit scary all at once.

How do you orchestrate this workflow? Do you define different skills that all use different models, or something else?

You should check out the PAL MCP and then also use this process, its super solid: https://github.com/glittercowboy/get-shit-done

The way "Phases" are handled is incredible with research then planning, then execution and no context rot because behind the scenes everything is being saved in a State.md file...

I'm on Phase 41 of my own project and the reliability and almost absence of any error is amazing. Investigate and see if its a fit for you. The PAL MCP you can setup to have Gemini with its large context review what Claude codes.

Post reply on HN