91–100 of 405 posts
They want to turn everything into a bootstrap framework, which is probably the limit of their mental horizon. And many people maintain that the emperor is fully clothed and that the scam works.
I had a preview of this over the weekend, notes here plus some example PRs: https://simonwillison.net/2025/Oct/20/claude-code-for-web/ It's really solid. It's effectively a web (and native mobile) UI over Claude Code CLI, more specifically "claude --dangerously-skip-permissions". Anthropic have recognized that Claude Code where you don't have to approve every step is massively more productive and interesting than the…
It’s interesting because I’ve slowly arrived at the opposite conclusion: for much of my practical day to day work, using CC with “allow edits” turned OFF results in a much better end product. I can correct it inline, I pseudo-review the code as it’s produced, etc etc. Codex is better for “fire and forget” features for sure. But Claude remains excellent at grokking intent for problems where you aren’t quite sure what…
Here's an example from this morning, getting CUDA working on a NVIDIA Spark: https://simonwillison.net/2025/Oct/20/deepseek-ocr-claude-co...
I have a few more in https://github.com/simonw/research
I feel like these background agents still aren't doing what I want from a developer experience perspective. Running in an inaccessible environment that pushes random things to branches that I then have to checkout locally doesn't feel great. AI coding should be tightly in the inner dev loop! PRs are a bad way to review and iterate on code. They are a last line of defense, not the primary way to develop. Give me an is…
Earlier quoted context omitted.
Yeah this has been my experience as well. The Claude Code UI is still so much better, and the permissioning policy system is much better. Though I'm working on closing that gap by writing a custom policy https://github.com/openai/codex/blob/main/codex-rs/execpolic... Kinda sick of Codex asking for approval to run tests for each test instance
You don't have to use Codex in its terminal UI - e.g. you can use it in the Zed IDE out-the-box: https://zed.dev/blog/codex-is-live-in-zed
Earlier quoted context omitted.
I can not. We're all racing very hard to take full advantage of these new capabilities before they go mainstream. And to be honest, sharing problem domains that are particularly attractive would be sharing too much. Go forth and experiment. Have fun with it. You'll figure it out pretty fast. You can read my other post here about the kinds of problem spaces I'm looking at.
I'm seeing the downvotes. I'm sorry folks feel that way. I'm regretting my honesty. Edit: I'd like to reply to this comment in particular but can't in a threaded reply, so will do that here: "Ah, super secret problem domains that have been thoroughly represented in the LLM training data. Nice." This exhibits a fundamental misunderstanding of why coding agents powered by LLMs are such a game changer. The assumption th…
The easier threading-focused approach to the conversation might be to add the additional comment as an edit at the end of the original and reply to the child https://news.ycombinator.com/item?id=45649068 directly. Of course, I've broken the ability to do that by responding to you now about it ;).
I had a preview of this over the weekend, notes here plus some example PRs: https://simonwillison.net/2025/Oct/20/claude-code-for-web/ It's really solid. It's effectively a web (and native mobile) UI over Claude Code CLI, more specifically "claude --dangerously-skip-permissions". Anthropic have recognized that Claude Code where you don't have to approve every step is massively more productive and interesting than the…
It’s interesting because I’ve slowly arrived at the opposite conclusion: for much of my practical day to day work, using CC with “allow edits” turned OFF results in a much better end product. I can correct it inline, I pseudo-review the code as it’s produced, etc etc. Codex is better for “fire and forget” features for sure. But Claude remains excellent at grokking intent for problems where you aren’t quite sure what…
Earlier quoted context omitted.
Do you find this to still be true with the Sonnet 4.5 model?
IMO Sonnet 4.5 is great but it just isn’t as comprehensive of a thinker. I love Anthropic and primarily use CC day to day but for any tricky problems or “high stakes, this must not have bugs” issues, I turn to Codex. I do find if you let Codex run on it its own too long it will produce comparably sloppy or lacking-in-vision type issues that people criticize Sonnet for, however.
We were heavy users of Claude Code ($70K+ spend per year) and have almost completely switched to codex CLI. I'm doing massive lifts with it on software that would never before have been feasible for me personally, or any team I've ever run. I'll use Claude Code maybe once every two weeks as a second set of eyes to inspect code and document a bug, with mixed success. But my experience has been that initially Claude Co…
Can you share an example of the tasks you found Codex being much better? From my experience Claude Code is much better.
We were heavy users of Claude Code ($70K+ spend per year) and have almost completely switched to codex CLI. I'm doing massive lifts with it on software that would never before have been feasible for me personally, or any team I've ever run. I'll use Claude Code maybe once every two weeks as a second set of eyes to inspect code and document a bug, with mixed success. But my experience has been that initially Claude Co…
Can you share an example of the tasks you found Codex being much better? From my experience Claude Code is much better.
Claude, especially 4.5 Sonnet, is a lot nicer to interact with, so it may be a better choice in cases where you are co-working with the agent. Its output is nicer, it "improvises" really well even if you give it only vague prompts. That's valueable for interactive use.
But for delegating complete tasks, Codex is far better. The benchmarks indicate that, as do most practicioners I talk to (and it is indeed my own experience).
In my own work, I use Codex for complete end-to-end tasks, and Claude Sonnet for interactive sessions. They're actually quite different.
Earlier quoted context omitted.
It’s interesting because I’ve slowly arrived at the opposite conclusion: for much of my practical day to day work, using CC with “allow edits” turned OFF results in a much better end product. I can correct it inline, I pseudo-review the code as it’s produced, etc etc. Codex is better for “fire and forget” features for sure. But Claude remains excellent at grokking intent for problems where you aren’t quite sure what…
That approach should work well for projects where you are directly working on the code in tandem with Claude, but a lot of my own uses are much more research oriented. I like sending Claude Code off on a mission figure out how to do something. Here's an example from this morning, getting CUDA working on a NVIDIA Spark: https://simonwillison.net/2025/Oct/20/deepseek-ocr-claude-co... I have a few more in https://github…