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

311–320 of 332 posts

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

#311

Post by pmarreck »

root_axis wrote: post #305
pmarreck wrote: post #277

Earlier quoted context omitted.

> This is exactly what I mean by folk magic. Incantations based on vibes So, true creativity, basically? lol I mean, the reason why programming is called a “craft” is because it is most definitely NOT a purely mechanistic mental process. But perhaps you still harbor that notion. Ah, I suddenly realized why half of all developers hate AI-assisted coding (I am in the other half). I was a Psych major, so code was always…

> So, true creativity, basically? lol Creativity is meaningless without well defined boundaries. > it is most definitely NOT a purely mechanistic mental process. So what? Nothing is. Even pure mathematics involves deep wells of creativity. > Ah, I suddenly realized why half of all developers hate AI-assisted coding Just to be clear, I don't hate AI assisted coding, I use it, and I find that it increases productivity…

I think Marvin Minsky had this same criticism of neural nets in general, and his opinion carried so much weight at the time that some believe he set back the research that led to the modern-day LLM by years.

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

#312

Post by sosjsbsb »

pmarreck wrote: post #310
sosjsbsb wrote: post #295

Earlier quoted context omitted.

> I was a Psych major, so code was always more “writing” than “gears” to me… It was ALWAYS “magic. The magic is supposed to disappear as you grow (or you’re not growing). The true magic of programming is you can actually understand what once was magic to you. This is the key difference I’ve seen my entire career - good devs intimately know “a layer below” where they work. > Perhaps because humans are also nondetermin…

I’m not talking about “magic” as in “I don’t understand how it works.” I’m talking “magic” as in “all that is LITERALLY happening is that bits are flipping and logic gates are FLOPping and mice are clicking and keyboards are clacking and pixels are changing colors in different patterns… and yet I can still spend hours playing games or working on some code that is meaningful to me and that other people sometimes like…

[dead]

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

#313

Post by theshrike79 »

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…

> - 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 me five rounds of repeatedly rewriting my prompt in various ways before I could get it to not code but just answer the question.

This has been an annoying Gemini feature since the beginning. I ask it to evaluate, check or analyse something, tab away and come back to it rewriting half the fucking codebase.

Please Google, use a percentage of your billions and add a "plan" mode to Gemini-cli - just like Claude has and I'd use your stuff a lot more often. The 1M context is excellent for large scale reviews, but its tendency to start writing code on its own is a pain in my ass.

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

#314

Post by theshrike79 »

embirico wrote: post #44
taurath wrote: post #10

These 2 sentences right next to each other stood out to me: > a new step towards becoming a reliable coding partner > GPT‑5.1-Codex-Max is built for long-running, detailed work Does this not sound contradictory? It’s been the shorter form work that has built what little confidence I have in these as a coding partner - a model that goes off and does work without supervision is not a partner to me.

(Disclaimer: Am on the Codex team.) We're basically trying to build a teammate that can do both short, iterative work with you, then as you build trust (and configuration), you can delegate longer tasks to it. The "# of model-generated tokens per response" chart in [the blog introducing gpt-5-codex]( https://openai.com/index/introducing-upgrades-to-codex/ ) shows an example of how we're improving the model good at bo…

My experience is completely different.

Codex(-cli) is an outsourced consultant who refuses to say "I can't do that" and will go to extreme lengths to complete a task fully before reporting anything. It's not a "teammate".

It also doesn't communicate much while it's working compared to Claude. So it's really hard to interrupt it while it's making a mistake.

Also, as a Go programmer, the sandbox is completely crazy. Codex can't access any of the Go module caches (in my home directory) and it has to result to crazy tricks to bring them INSIDE the project directory - which it keeps forgetting to do (as the commands have to run with specific ENV_VARS) and just ... doesn't run tests for example, because it couldn't.

The only way I've found to make that problem go away is run it with the --omg-super-dangerous-give-every-permission-ever switch just so that it can do the basic work I need it to do.

Maybe give us an option between the ultra-safe sandbox that just refused to run "ps" 15 minutes ago to check if a process is running and the "let me do anything anywhere" option. Some sane defaults please.

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

#315

Post by theshrike79 »

roflcopter69 wrote: post #262
Narciss wrote: post #168

Earlier quoted context omitted.

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.

It's just convenience really. Context7 takes care of keeping _all_ the documentation available and provides a search function.

You can definitely have it locally or even build a RAG/MCP -thing just for the specific docs you want.

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

#316

Post by theshrike79 »

epolanski wrote: post #135

Small ot question on the GPT cli tool. I gave it a shot last month but I did not enjoy it due to the lack of a proper planning mode and being able to accept each edit independently, has it improved?

No. Claude is still the only CLI agent tool with a planning mode.

Crush, Gemini, Codex and Copilot don't have it for some reason. Can't be that difficult

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

#317

Post by theshrike79 »

levocardia wrote: post #61
syntaxing wrote: post #46

I rarely used Codex compared to Claude because it was extremely slow in GitHub copilot . Like maybe 2-5X slower than Claude Sonnet. I really wish they just made their models faster than “better”

Very interesting to see the range of peoples' preferences. I would almost always prefer smart over fast; I have all my LLMs to be all-thinking-all-the-time.

Depends on what I'm doing.

If I'm adding a new feature I want to test and keep the flow going, I want fast -> Claude.

But if I want a report on test coverage or possible security issues or a bigger refactoring, I want slow careful and smart -> Codex.

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

#318

Post by theshrike79 »

nartho wrote: post #48
syntaxing wrote: post #46

I rarely used Codex compared to Claude because it was extremely slow in GitHub copilot . Like maybe 2-5X slower than Claude Sonnet. I really wish they just made their models faster than “better”

Have you tried Mistral ? Definitely one of the fastest models

I've tried Mistral for coding and it seems to be laughably bad every time. Dunno what I'm doing wrong.

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

#319

Post by 999900000999 »

roflcopter69 wrote: post #263
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?

It works really really well!

I can have it do changes via a Copilot Pull Request on GitHub and deploy it straight to itch without me touching the code.

I’m using Web builds.

The only thing that’s weird is I literally got screenshots from to work on the PRs once or twice and then it stopped working.

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

#320

Post by scastillo »

bobbylarrybobby wrote: post #196
scastillo wrote: post #193

Earlier quoted context omitted.

This is just how the attention mechanism works. (search for effective context problem for more info. e.g. https://arxiv.org/abs/2509.21361 ) To solve it, you just don't allow your current context to use more than 50% of the total window size To do that in Claude code, you have to use subagents and design small enough agents Then you can use skills to make it remember every time the little details or the steps More ef…

Are agents still the way to go or have skills supplanted them? I don't really understand when you'd use one or the other

It's better if you think that the only thing that is really there is a context window.

They can add complex concepts and tools on top, but all that is is a different way to put things in the context window. Even the chat history on the web... You are not sending a message every time... It's not really a chat... the model is writing what it predicts will come next, like autocompleting a Word document that is written in a chat-like format.

So agents are like you, opening a new window and having the chat there, so you don't pollute the current window with all the tokens needed to process that question, and to use only the output here.

This is important bc of the effective context window problem. Models are more accurate the smaller the context is.

Hence, MCP tools are problematic. If you have registered many of them, the rules for using each one are added to your context, even if you don't use them.

Having a very extensive Claude.md file is also problematic.

You can use skills to instruct the model on which agents to use when requesting a specific thing. Antrophic says they have trained the model to discover on its own when to read the skill and follow the instructions you picture there, which can include Python scripts to run.

So yeah, agents help the model save context window for your current problem, skills help the model follow your instructions better, and instructions can include agent calling, and MCP is crap, you'd better ask the model to generate code to make that call

Oh, there are also slash commands. I don't really use them... if someone has a success story for them, I would love to know about it.

Post reply on HN