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

Building more with GPT-5.1-Codex-Max

openai.com

Post reply on HN
Print view View original

261–270 of 332 posts

Re: Building more with GPT-5.1-Codex-Max

#261

Post by Topfi »

johnfn wrote: post #56

I've been using a lot of Claude and Codex recently. One huge difference I notice between Codex and Claude code is that, while Claude basically disregards your instructions (CLAUDE.md) entirely, Codex is extremely, painfully, doggedly persistent in following every last character of them - to the point that i've seen it work for 30 minutes to convolute some solution that was only convoluted because of some sentence I t…

> If you ask Claude to fix a test that accidentally says assert(1 + 1 === 3), it'll say "this is clearly a typo" and just rewrite the test. Codex will rewrite the entire V8 engine to break arithmetic.

Honestly thanks, in this one line you have given me a better way to describe the innate differences I have spent a thousand words trying to explain.

Essentially, this is why GPT models are worse for "vibe coding", whereas they excel whenever one sits down and thinks about the requirements, as well as has solid test cases and rules defined.

Re: Building more with GPT-5.1-Codex-Max

#262

Post by roflcopter69 »

Narciss wrote: post #168
999900000999 wrote: post #94

I really would prefer them to start creating customized models. I've vibe coded Godot games extensively. Just about every model I've tried likes to invent imaginary functions. I was really prefer for there to be a way for me to pick model trained in whatever framework I need. Reviewing AI generated code feels like editing a long book, and every now and then you notice some words are just completely made up. You then…

Context7 might be good for you

Just curious, wouldn't it be easier to download the docs in a format that is searchable for the LLM? A MCP for this seems overkill to me.

Re: Building more with GPT-5.1-Codex-Max

#263

Post by roflcopter69 »

999900000999 wrote: post #94

I really would prefer them to start creating customized models. I've vibe coded Godot games extensively. Just about every model I've tried likes to invent imaginary functions. I was really prefer for there to be a way for me to pick model trained in whatever framework I need. Reviewing AI generated code feels like editing a long book, and every now and then you notice some words are just completely made up. You then…

How well has your vibecoding with Godot worked? I thought about it but wouldn't the LLM be unable to add files by itself due to stuff only the Godot editor knows how to do like generating uid files and so on? I would have expected that the LLM needs a MCP or some tool calling to properly interact with a Godot project. How are you doing it?

Re: Building more with GPT-5.1-Codex-Max

#264

Post by roflcopter69 »

machiaweliczny wrote: post #247
machiaweliczny wrote: post #246

Earlier quoted context omitted.

Just add godot example games nearby and it will learn functions / usecase from them. Just say in instructions BTW you have example games in "examples" directory to check

You can also use "repomix" tool to bundle whole source of godot into single file and tell it to search it when uncertain

Why use an extra tool, when you can tell the LLM where the Godot source is to be found in case it wants to investigate some details? What is the benefit of using repomix?

Re: Building more with GPT-5.1-Codex-Max

#265

Post by jack_pp »

root_axis wrote: post #236
jack_pp wrote: post #224

Earlier quoted context omitted.

I view it more as fun and spicy. Now we are moving away from the paradigm that the computer is "the dumbest thing in existence" and that requires a bit of flailing around which is exciting! Folk magic is (IMO) a necessary step in our understanding of these new.. magical.. tools.

I won't begrudge anyone having fun with their tools, but folk magic definitely isn't a necessary step for understanding anything, it's one step removed from astrology.

I'd say the only ones capable of really approaching anything like scientific understanding of how to prompt these for maximum efficacy are the providers not the users.

Users can get a glimpse and can try their best to be scientific in their approach however the tool is of such complexity that we can barely skim the surface of what's possible.

That is why you see "folk magic", people love to share anecdata because.. that's what most people have. They either don't have the patience, the training or simply the time to approach these tools with rational rigor.

Frankly it would be enormously costly in both time and API costs to get anywhere near best practices backed up by experimental data let alone having coherent and valid theories about why a prompt technique works the way it does. And even if you built up this understanding or set of techniques they might only work for one specific model. You might have to start all over again in a couple of months

Re: Building more with GPT-5.1-Codex-Max

#266

Post by d4rkp4ttern »

EnPissant wrote: post #25
hansonw wrote: post #15

Rest assured that we are better at training models than naming them ;D - New benchmark SOTAs with 77.9% on SWE-Bench-Verified, 79.9% on SWE-Lancer, and 58.1% on TerminalBench 2.0 - Natively trained to work across many hours across multiple context windows via compaction - 30% more token-efficient at the same reasoning level across many tasks Let us know what you think!

Compaction is just what Claude Code has done forever, right?

My understanding is that they trained it to explicitly use a self-prune/self-edit tool that trims/summarizes portions of its message history (e.g. use tool results from file explorations, messages that are no longer relevant, etc) during the session, rather than "panic-compact" at the end. In any case, it would be good if it does something like this.

Re: Building more with GPT-5.1-Codex-Max

#267

Post by wild_egg »

int_19h wrote: post #222
wild_egg wrote: post #214

Earlier quoted context omitted.

They're completely orthogonal features. Skills are just reusable prompts in a convenient package. Subagents get their own pristine context window to go off and perform some task. They can also run skills and do lots of context-heavy work and report back some small sliver of it to the main agent as a report.

Skills are more than just reusable prompts, since they can be packaged alongside with runnable Python or Node scripts that the model can use to achieve what it needs.

Not just Python and Node. Package anything you want with them, that's what makes them convenient.

Re: Building more with GPT-5.1-Codex-Max

#268

Post by simonw »

mjburgess wrote: post #245
simonw wrote: post #99

Thinking level medium: https://tools.simonwillison.net/svg-render#%3Csvg%20xmlns%3D... Thinking level xhigh: https://tools.simonwillison.net/svg-render#%20%20%3Csvg%20xm...

Given that its likely this sort of SVG output has been RLHF special-cased, I think it's time we move past this benchmark.

I don't think it's invalid yet. Those pelicans still kind of suck!

https://simonwillison.net/2025/Nov/13/training-for-pelicans-...

Re: Building more with GPT-5.1-Codex-Max

#269

Post by ghosty141 »

the_duke wrote: post #207
jwpapi wrote: post #190

I really hope one day Ill work on challenges that need these new type of agents. Currently, I either need a fast agent that does what I want faster than I can type it (CRUD, forms, etc) or I need an agent to discuss a plan, ups and downs. Whenever I try to give it a bigger task it takes a lot of time, and often is not what I’ve expected, which might be totally my fault or context specific, but as soon as I’m able to…

The key is learning how to provide proper instructions. Treat it as a developer that just joined the project and isn't aware of the conventions. Provide hints for the desired API design, mention relevant code locations that should be read to gain context on the problem, or that do similar things. An AGENTS.md that explains the project and provides some general guidelines also helps a lot. Codex can be incredibly stro…

This is generally the right approach imo (when it comes to codex).

In my experience Codex is pretty "bad" at spotting conventions or already existing code. Yesterday I told him a feature to implement (maybe 40 loc?) and he 1. did added unnecessary atomics and 2. he kinda reimplemented a function that already existed that he should've just reused.

I told him that and he fixed it but these are the things that kinda hold AI back by a lot. It's MUCH harder to read code than to write it, and if he writes the code I must 100% understand it to have the same confidence in it as if I did it myself. And that to me is mentally almost more taxing than doing it myself.

If you just let codex write the code while instructing him exactly what you want in terms of logic and architecture it works really well and saves a on of typing.

Re: Building more with GPT-5.1-Codex-Max

#270

Post by jdthedisciple »

boole1854 wrote: post #155

Today I did some comparisons of GPT-5.1-Codex-Max (on high) in the Codex CLI versus Gemini 3 Pro in the Gemini CLI. - As a general observation, Gemini is less easy to work with as a collaborator. If I ask the same question to both models, Codex will answer the question. Gemini will read some intention behind the question, write code to implement the intention, and only then answer the question. In one case, it took m…

This tells you all you need to know about benchmarks:

Didn't Google proudly tout their Gemini 3 as beating everything under the sun in every benchmark imaginable by a margin?

Post reply on HN