511–520 of 634 posts
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]"
Earlier quoted context omitted.
All of them can do it but Codex has the least frustrating usage limits.
When using it in VSCode? The browser system running its own container seems like it would be the most demanding on their resources. The stand-alone client is Mac-only but I don't know if it makes a difference. My goal is to do it within the usage I get from a $20 monthly plan.
Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic. I guess it’s a matter of focus and being provided with a smaller set of code to tackle.
I want to recompile a Rust project to be f32 instead of f64. Am I better off buying 1 month of Codex, Claude, or Antigravity? I want to have the agent continuesly recompile and fix compile errors on loop until all the bugs from switching to f32 are gone.
Between Codex and Claude, Codex will have much more generous limits for the same price, especially if you use top-of-the-line models (although for your task, Sonnet might actually be good enough).
lmao so cringe that they delay releasing the model until anthropic does
Earlier quoted context omitted.
> it's a waste of time to steer them It's not a waste of time, it's a responsibility. All things need steering, even humans -- there's only so much precision that can be extrapolated from prompts, and as the tasks get bigger, small deviations can turn into very large mistakes. There's a balance to strike between micro-management and no steering at all.
The prompt is decreasingly relevant. The verification environment you have is what actually matters.
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 specs. It's all a game of information.
It is absurd to release 5.3-Codex before first releasing 5.3. Also, there is no reason for OpenAI and Anthropic to be trying to one-up each other's releases on the same day. It is hell for the reader.
Earlier quoted context omitted.
I think it's the opposite. Especially considering Codex started out as a web app that offers very little interactivity: you are supposed to drop a request and let it run automatously in a containerized environment; you can then follow up on it via chat --- no interactive code editing.
Fair I agree that was true of early codex and my perception too.. but today there are two announcements that came out and thats what im referring to. specifically, the GPT-5.3 post explicitly leans into "interactive collaborator" langauge and steering mid execution OpenAI post: "Much like a colleague, you can steer and interact with GPT-5.3-Codex while it’s working, without losing context." OpenAI post: "Instead of w…
On further prompting it did the next step and terminated early again after printing how it would proceed.
It's most likely just a bug in GitHub Copilot, but it seems weird to me that they add models that clearly don't even work with their agentic harness.
Earlier quoted context omitted.
There are plenty of companies that sell an AI assistant that answers the phone as a service, they just aren't named OpenAI or Anthropic. They'll let callers book an appointment onto your calendar, even!
No, there are companies that sell voice activated phone trees, but no one is getting results out of unstructured, arbitrary phone call answering with actions taken by an LLM. I'm sure there are research demos in big companies, I'm sure some AI bro has done this with the Twilio API, but no one is seriously doing this. All it takes is one "can you take this to the post office", the simplest, of requests, and you're in…
What does work in production (at least for SMB/customer-support style calls) is making the problem less magical: 1) narrow domain + explicit capabilities (book/reschedule/cancel, take a message, basic FAQs) 2) strict tool whitelist + typed schemas + confirmations for side effects 3) robust out-of-scope detection + graceful handoff (“I can’t do that, but I can X/Y/Z”) 4) real logs + eval/test harnesses so regressions get caught
Once you do that, you can get genuinely useful outcomes without the role-play traps you’re describing.
We’ve been building this at eboo.ai (voice agents for businesses). If you’re curious, happy to share the guardrails/eval setup we’ve found most effective.