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

611–620 of 634 posts

Re: GPT-5.3-Codex

#611

Post by freakynit »

adrianN wrote: post #587
freakynit wrote: post #517

Earlier quoted context omitted.

I think this all comes down to information. Most prompts we give are severely information-deficient. The reason LLMs can still produce acceptable results is because they compensate with their prior training and background knowledge. The same applies to verification: it's fundamentally an information problem. You see this exact dynamic when delegating work to humans. That's why good teams rely on extremely detailed sp…

Having prompts be information deficient is the whole point of LLMs. The only complete description of a typical programming problem is the final code or an equivalent formal specification.

Exactly the point. But, LLM's miss that human intuition part.

Re: GPT-5.3-Codex

#612

Post by cheriot »

maxkfranz wrote: post #572
cheriot wrote: post #498

Page me when codex can run the right version of node. Are we all changing the system node version to match the current project again? [shell_environment_policy] inherit = "all" experimental_use_profile = true [shell_environment_policy.set] NVM_DIR = "[redacted]" PATH = "[redacted]"

It worked for me after I configured mise. I needed the mise setup in both `.zprofile` and `.zshrc` for Codex to pick it up. I think mise sets up itself in one of those by default, but Codex uses the other. I expect the same problem would present itself with nvm. I.e. `eval "$(/Users/max/.local/bin/mise activate zsh)"` in `.zprofile` and `.zshrc` Then Codex will respect whatever node you've set as default, e.g.: mise…

Thanks! I moved my PATH setup to .zprofile and everything works now. Brew had added itself to .zprofile and everything else was in .zshrc.

Re: GPT-5.3-Codex

#613

Post by cheriot »

Sn0wCoder wrote: post #608
cheriot wrote: post #498

Page me when codex can run the right version of node. Are we all changing the system node version to match the current project again? [shell_environment_policy] inherit = "all" experimental_use_profile = true [shell_environment_policy.set] NVM_DIR = "[redacted]" PATH = "[redacted]"

If you are already using Volta in your project Codex will use the correct version assuming you are running in the same directory as your .json file and the json file has the” volta”:{ “node”: “xx.x.x”, “npm”: “xx.x.x”} configured. Personally use a Dockerfile to setup the container with volta installed. Need to set up Volta and configure at least one version of Node then install Codex in the docker. One caveat is you…

Codex is using a login shell so moving my PATH setup to .zprofile fixed it (previously was in .zshrc). Now we just need to write this on the internet enough times that future codex can suggest the fix :p

Re: GPT-5.3-Codex

#614

Post by energy123 »

benry1 wrote: post #557
energy123 wrote: post #418

Earlier quoted context omitted.

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

I'm reading Maintenance of Everything and it has a section about the switch from artisan-crafted weapons to making uniform parts that feels comparable to this. French military had pioneered a way to make fully interchangeable weapon parts, but the French public fought back in fear of the jobs of the artisans who used to hand-make weapons. Over the next 20 years they completely lost their edge on the battlefield, noth…

> The artisans stopped being people who made weapons, the artisans became people who made machines that made weapons.

Although many French artisans become unemployed because British industrial productivity made them uncompetitive. It was one of the causes of the French Revolution.

Re: GPT-5.3-Codex

#615

Post by maxkfranz »

cheriot wrote: post #612
maxkfranz wrote: post #572

Earlier quoted context omitted.

It worked for me after I configured mise. I needed the mise setup in both `.zprofile` and `.zshrc` for Codex to pick it up. I think mise sets up itself in one of those by default, but Codex uses the other. I expect the same problem would present itself with nvm. I.e. `eval "$(/Users/max/.local/bin/mise activate zsh)"` in `.zprofile` and `.zshrc` Then Codex will respect whatever node you've set as default, e.g.: mise…

Thanks! I moved my PATH setup to .zprofile and everything works now. Brew had added itself to .zprofile and everything else was in .zshrc.

Glad it worked out. And I agree it’s annoying that this doesn’t just work out of the box. It’s not like node/nvm are uncommon, so you’d think they would have ran into the issue when using their own tool.

Re: GPT-5.3-Codex

#616

Post by nurettin »

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 wouldn't say that anything before 11/2025 was a game changer, but after that, wow.

That said, I wouldn't expect there to be an innovative solution to an unsolved problem written by AI or humans that has been open sourced within the past 3 months.

Re: GPT-5.3-Codex

#617

Post by zen4ttitude »

mercnz wrote: post #448
xd1936 wrote: 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.

well with the recent delays i can easily find claude code going off on it's own for 20 minutes and have no idea what it's going to come back with. but one time it overflowed it's context on a simple question, and then used up the rest of my session window. in a way a lot of ai assistants have ime have this awkward thing where they complicate something in a non-visible and think about it for a long time burning up con…

For complex tasks I ask ChatGPT or Grok to define context then I take it to Claude for accurate execution. I also created a complete pipeline to use locally and enrich with skills, agents, RAG, profiles. It is slower but very good. There is no magic, the richer the context window the more precise and contained the execution.

Re: GPT-5.3-Codex

#618

Post by zen4ttitude »

Does anyone know more about the benchmark? 60% accuracy gets a drumroll? How would Claude do? How would a human do? I tried the previous version and was not impressed. I went back to Claude that is very hard to beat, and versatile with context enrichment.

Re: GPT-5.3-Codex

#619

Post by ifwinterco »

Rapzid wrote: post #485
ifwinterco wrote: post #342

Earlier quoted context omitted.

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.

I just don't use any Microsoft software anymore, thankfully

Re: GPT-5.3-Codex

#620

Post by _zoltan_ »

retinaros wrote: post #602
_zoltan_ wrote: post #297

Earlier quoted context omitted.

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.

good luck.

I've been working on very complex problems with this model and the results I have have surprised people over and over again.
Post reply on HN