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

41–50 of 431 posts

Re: Claude Code 2.0

#41

Post by haefeledev »

j1elo wrote: post #33

Prompt: https://raw.githubusercontent.com/marckrenn/cc-mvp-prompts/r... I've always been curious. Are tags like that one: " " useful at all? Is the LLM training altered to give a special meaning to specific tags when they are found? Can a user just write those magic tags (if they knew what they are) and alter the behavior of the LLM in a similar manner?

I think they specifically trained claude on any kind of xml tags (see their docs https://docs.claude.com/en/docs/build-with-claude/prompt-eng...)

Re: Claude Code 2.0

#42

Post by cube2222 »

j1elo wrote: post #33

Prompt: https://raw.githubusercontent.com/marckrenn/cc-mvp-prompts/r... I've always been curious. Are tags like that one: " " useful at all? Is the LLM training altered to give a special meaning to specific tags when they are found? Can a user just write those magic tags (if they knew what they are) and alter the behavior of the LLM in a similar manner?

Claude tends to work well with such semi-xml tags in practice (probably trained for it?).

You can just make them up, and ask it to respond with specific tags, too.

Like “Please respond with the name in … tags and the .”

It’s one of the approaches to forcing structured responses, or making it role-play multiple actors in one response (having each role in its tags), or asking it to do a round of self-critique in tags before the final response, etc.

Re: Claude Code 2.0

#44

Post by jspdown »

spike021 wrote: post #21
jakozaur wrote: post #17

Just use `claude update` if you already have it. Unfortunately, they removed Plan mode, when I could use Opus for planning and Sonnect for coding. Though I will see how this pans out.

is Plan mode any different from telling Claude "this is what I'd like to do, please describe an implementation plan"? that's generally my workflow and I have the results saved into a CLAUDE-X-plan.md. then review the plan and incrementally change it if the initial plan isn't right.

There's a bit of UI around it where you can accept the plan. I personally stopped using it and instead moved to a workflow where I simply ask it to write the plan in a file. It's much easier to edit and improve this way.

Re: Claude Code 2.0

#45

Post by alecco »

As a burnt-out, laid-off aging developer, I want to thank Anthropic for helping me get in love with programming again. Claude Code on terminal with all my beloved *nix tools and vim rocks.

Re: Claude Code 2.0

#46

Post by xmpirate »

I wish there were an option to cancel a currently running prompt midway. Right now, pressing Ctrl+C twice ends up terminating the entire session instead.

Re: Claude Code 2.0

#49

Post by simonw »

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 don't know how to isolate them in a safe container but wow the stuff you can do with them is fascinating.

Post reply on HN