Live data from Hacker News

Claude Code on the web

anthropic.com

261–270 of 405 posts

Re: Claude Code on the web

#261

This is quite nice! I'm using Claude Code locally a lot, occasionally with a couple parallel session. I was very happy when they made the GitHub Action - I used it quite a bit, but in practice I got frustrated that I effectively only get a single back-and-forth out of it, I can't really "continue the conversation without losing context" - Sure, I can respond to it in the PR it makes, but that will be a fresh session…

You can ask Claude to install Postgres and it should just work. We'll have it. In the default image shortly.

Re: Claude Code on the web

#262
post #208

This is going to be extremely useful. A lot of people have hacked together similar things to get around waiting for CC to finish without mangling worktrees and branches manually. I was curious how the 'Open in CLI' works - it copies a command to clipboard like 'claude --teleport session_XXXXX', which opens the same chat in the CLI, and checks out a new branch off origin/main which it's created for the thread, called…

Our title generation is done preemptively as you type and is a bit too eager to declare it has enough context. We’ll tweak it.

Re: Claude Code on the web

#265

The way network Access works really feels weird to me. I wish that instead i could just do it like (or with!) nix. If i know the hash of the thing I'm fetching from the network, allow me access to it. Instead of arbitrarily allow listing domains. Imagine if this would just be able to use your nix file in your repo to fetch all the dependencies needed to run your project. That'd be extremely sick

Thanks for the suggestion! We’re working on making this smoother.

Re: Claude Code on the web

#267
post #144

Earlier quoted context omitted.

I find Codex CLI to be very good too, but it’s missing tons of features that I use in Claude Code daily that keep me from switching full time. - Good bash command permission system - Rollbacks coupled with conversation and code - Easy switching between approval modes (Claude had a keybind that makes this easy) - Ability to send messages while it’s working (Codex just queues them up for after it’s done, Claude injects…

I don't think anyone can reasonably argue against Claude Code being the most full-featured and pleasant to use of the CLI coding agent tools. Maybe some people like the Codex user experience for idiosyncratic reasons, but it (like Gemini CLI) still feels to me rather thrown together - a Claude Clone with a lot of rough edges. But these CLI tools are still fairly thin wrappers around an LLM. Remember: they're "just an…

Thick or thin, the wrapper so that users aren't manually copy and pasting code around is material to it being used and useful. Plus the systems prompt is custom to each tool and greatly affect how well the tool works.

Re: Claude Code on the web

#268

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…

Im not saying this is a paid endorsement but the internet is dead and I wonder what openAI would pay, if they could, to get such a glowing review as top comment on HN

The only way to tell human from AI now is disagreeableness, it’s the one thing the GPTs refuse to do. I can’t stand their cloying sycophancy but at least it means that serial complainers will gain some trust, at least for as long as Americans are leading the hunt and deciding to baby us.

Re: Claude Code on the web

#269
post #89

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…

Hey, Kanjun from Imbue here! This is exactly why we built Sculptor (https://imbue.com/sculptor), a desktop UI for Claude Code.

Each agent has its own isolated container. With Pairing Mode, you can sync the agent's code and git state directly into your local Cursor/any IDE so you can instantly validate its work. The sync is bidirectional so your local changes flow back to the agent in realtime.

Happy to answer any questions - I think you'll really like the tight feedback loop :)

Re: Claude Code on the web

#270
I wish that a "Claude Code"-session (and a per-project-id session) could present itself in Claude Web in menu entries to create new chats which participate in the selected Claude Code session.
Post reply on HN