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

71–80 of 431 posts

Re: Claude Code 2.0

#71

Post by rancar2 »

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?

A user can append similar system reminders in their own prompt. It’s one of the things that the Claude Code team discovered worked and now included in other CLIs like Factory, which was talked about today by cofounder of Factory: https://www.youtube.com/live/o4FuKJ_7Ds4?si=py2QC_UWcuDe7vPN

Re: Claude Code 2.0

#72

Post by jckahn »

aeon_ai wrote: post #31

To those lamenting that the Plan with Opus/Code with Sonnet feature is not available, check the charts. Sonnet 4.5 is beating Opus 4.1 on many benchmarks. Feels like it's a change they made not to 'remove options', but because it's currently universally better to just let Sonnet rip.

Sure but I want to review the ripping plan so it tears along the correct lines.

Re: Claude Code 2.0

#73

Post by lukev »

lupusreal wrote: post #23
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.

> Unfortunately, they removed Plan mode WTF. Terrible decision if true. I don't see that in the changelog though

No. Plan mode still works fine.

They just changed it so you can't set it to use Opus in planning mode... it uses Sonnet 4.5 for both.

Which makes sense Iif it really is a stronger and cheaper model.

Re: Claude Code 2.0

#74

Post by freeqaz »

gdudeman wrote: post #66
jmward01 wrote: post #57

"When you use Claude Code, we collect feedback, which includes usage data (such as code acceptance or rejections), associated conversation data, and user feedback submitted via the /bug command." So I can opt out of training, but they still save the conversation? Why can't they just not use my data when I pay for things. I am tired of paying, and then them stealing my information. Tell you what, create a free tier th…

This enables the /resume command that lets you start mid-conversation again. Storing the data is not the same as stealing. It's helpful for many use cases. I suppose they should have a way to delete conversations though.

That's not just them saving it locally to like `~/.claude/conversations`? Feels weird if all conversations are uploaded to the cloud + retained forever.

Re: Claude Code 2.0

#75

Post by cesarvarela »

xmpirate wrote: post #46

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.

Adding to the press Esc comments, if you press it twice, you can revert to previous messages in the current conversation.

Re: Claude Code 2.0

#76

Post by lupusreal »

alecco wrote: post #45

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.

Agreed, it's actually fun again. The evening hours I used to burn with video games and weed are now spent with claude code, rewriting and finishing up all my custom desktop tools and utilities I started years ago.

Re: Claude Code 2.0

#80

Post by itsmevictor »

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?

> If you do not use this tool when planning, you may forget to do important tasks - and that is _unacceptable_.

Okay, I know I shouldn't anthropomorphize, but I couldn't prevent myself from thinking that this was a bit of a harsh way of saying things :(

Post reply on HN