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

Claude Code 2.0

npmjs.com

Post reply on HN
Print view View original

291–300 of 431 posts

Re: Claude Code 2.0

#291

Post by hboon »

polyrand wrote: post #260
simonw wrote: post #49

Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…

Instead of containers, which may not always be available, I'm experimenting with having control over the shell to whitelist the commands that the LLM can run [0]. Similar to an allow list, but configured outside the terminal agent. Also trying to make it easy to use the same technique in macOS and Linux [0]: https://ricardoanderegg.com/posts/control-shell-permissions-...

I didn’t check, but sometimes Claude Code writes scripts and run them (their decision); does your approach guard against that?

Re: Claude Code 2.0

#292

Post by raphman »

globular-toast wrote: post #257
athrowaway3z wrote: post #62

Earlier quoted context omitted.

They're only as dangerous as the capabilities you give them. I just created a `codex` and `claude` user on my Linux box and practically always run in yolo mode. I've not had a problem so far. Also, I think shellagent sounds cooler.

I tried this but it's incredibly annoying as you'll get a mixture of file ownerships and permissions. Instead I run it in bubblewrap sandbox: https://blog.gpkb.org/posts/ai-agent-sandbox/

Thanks - seems to work quite well.

Re: Claude Code 2.0

#293

Post by sbene970 »

cadamsdotcom wrote: post #207

Claude Code is so much better than anything else. If Claude Code was a car it'd be the ideal practical vehicle for all kinds of uses. If OpenAI Codex was a car, it'd be a cauldron with wheels. The reason I say this is CC offers so many features: plan mode, hooks, escape OR ctrl-c to interrupt it, and today added quick rewind. Meanwhile Codex can't even wrap text to the width of the terminal; you can't type to it whil…

I agree, CC is much more polished regarding UX. I can't even scroll up in codex CLI, which is just a disaster IMO.

Re: Claude Code 2.0

#294

Post by Danjoe4 »

esperent wrote: post #198
arjie wrote: post #89

I really like these tools. Yesterday I gave it a filename for a video of my infant daughter eating which I took while I had my phone on the charger. The top of the charger slightly obscured the video. I told it to crop the video to just her and remove the obscured portion and that I had ffmpeg and imagemagick installed and it looked at the video, found the crop dimensions, then ran ffmpeg and I had a video of her all…

Cline extension can use Grok, in fact I think it's free at the moment. I tried Claude Code and Cline for similar tasks and found Claude Code incredibly expensive but not better, so I've been sticking with Cline and switching between APIs depending on what model currently has the vest price/performance going on.

I wish the Cline extension was more performant. It has a 1000+ ms startup time for VScode and stutters occasionally. In terms of workflow though, it's my absolute favorite. I simply don't think the models are there yet for fully agentic coding in any reasonably complex/novel codebase. Cline lets me supervise the LLM step by step.

Re: Claude Code 2.0

#295

Post by ozgung »

simonw wrote: post #49

Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…

> Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer.

One criticism on current generation of AI is that they have no real world experience. Well, they have enormous amount of digital world experience. That, actually, has more economical value.

Re: Claude Code 2.0

#297

Post by nsonha »

jspdown wrote: post #47
mentalgear wrote: post #19

Well I guess I'll be sticking with opencode.

Do you mind telling us a bit more? I never used OpenCode, what makes it better in your opinion?

- opensource with an SDK so you can build things on top of

- supports every LLM provider under the sun, including Anthropic

- has built-in LSP support https://opencode.ai/docs/lsp

Re: Claude Code 2.0

#299

Post by dandaka »

ranguna wrote: post #279
f311a wrote: post #249

It still bothers me that almost every agentic TUI is written in TS + React. It often consumes at least a few GB of RAM. No one bothers about it. Everybody is trying to ship as fast as possible.

They use react on a cli tool?

Yes, the library is @vadimdemedes/ink, which uses React to render components

Re: Claude Code 2.0

#300

Post by ACCount37 »

simonw wrote: post #49

Something I realized about this category of tool (I call them "terminal agents" but that already doesn't work now there's an official VS Code extension for this - maybe just "coding agents" instead) is that they're actually an interesting form of general agent . Claude Code, Codex CLI etc can effectively do anything that a human could do by typing commands into a computer. They're incredibly dangerous to use if you d…

Back in 2022, when ChatGPT was new, quite a few people were saying "LLMs are inherently safe because they can't do anything other than write text". Some must have even believed what they were saying.

Clearly not. Just put an LLM into some basic scaffolding and you get an agent. And as capabilities of those AI agents grow, so would the degree of autonomy people tend to give them.

Post reply on HN