Out of all changes I want the most is to not need to type `\ ` to make a line break.
codex has control-J
others say here that option/alt-enter may work? not sure why shift-enter couldn't though.
Claude Code 2.0
361–370 of 431 posts
Re: Claude Code 2.0
#362FINALLY checkpoints! All around good changes, Claude Code is IMHO the best of the LLM CLI tools.
I already set up a jj (jujutsu) repo in my projects colocated with git (it uses git for its backend). Once you additionally set up a certain background daemon, it will then autocommit (label-lessly) every change to every file in that project. So you get "infinite undo", basically. It's actually more powerful than this checkpointing idea.
Re: Claude Code 2.0
#363Earlier quoted context omitted.
You can rewind your context back to the checkpoint
No, that's not the point of this new checkpoints feature. It's already been possible for a while to rewind context in Claude Code by pressing . This feature rewinds code state alongside context : > Our new checkpoint system automatically saves your code state before each change , and you can instantly rewind to previous versions by tapping Esc twice or using the /rewind command. https://www.anthropic.com/news/enablin…
Since they recommend still using version control anyway, looks like I will stick to my solution of using a git-colocated jj (jujutsu) SCM which automatically makes label-less (no commit message) commits with every file change to every tracked file (new files are automatically tracked). So you get infinite undo.
Re: Claude Code 2.0
#364Out of all changes I want the most is to not need to type `\ ` to make a line break.
Assuming you aren't using windows terminal: launch claude code and run `/terminal-setup` -- that will enable shift+enter
Re: Claude Code 2.0
#365Earlier quoted context omitted.
It is dangerous. Just yesterday my cursor agent made some changes to a live kubernetes cluster even over my specific instruction not to. I gave it kubectl to analyze and find the issues with a large Prometheud + AlertManager configuration, then switched windows to work on something else. When I was back the MF was patching live resources to try and diagnose the issue.
Best way to avoid this is to force the LLM to use git branches for new work. Worst case scenario you lose some cash on tokens and have to toss the branch but your prod system is left unscathed.
I thought the general point is that you can't "force" an LLM to stay within certain boundaries without placing it in an environment where it literally has no other choice.
(Having said that, I'm just a kibitzer.)
Re: Claude Code 2.0
#366Out of all changes I want the most is to not need to type `\ ` to make a line break.
If you're on Windows and using vscode, add thiss to keybinds.json
[ { "key": "shift+enter", "command": "workbench.action.terminal.sendSequence", "args": { "text": "\u001b\n" }, "when": "terminalFocus" }, ]
It will allow you to get new lines without any strange output.
Re: Claude Code 2.0
#367Earlier quoted context omitted.
Incredibly dangerous to use? Seems like a wild exaggeration. I’ve been using Claude code since launch, must have used it for 1000 hours or more by now, and it’s never done anything I didn’t want it to do. Why would I run it in a sandbox? It writes code for me and occasionally runs a build and tests. I’m not sure why you’re so fixated on the “danger”, when you use these things all the time you end up realizing that th…
You've been safe since launch because you haven't faced an adversarial prompt injection attack yet. You (and many, many others) likely won't take this threat seriously until adversarial attacks become common. Right now, outside of security researcher proof of concepts, they're still vanishingly rare. You ask why I'm obsessed with the danger? That's because I've been tracking prompt injection - and our total failure t…
how are you going to get "adversarial attacks" with prompt injection. If you don't fetch data from external sources. Web scraping ( you can channel that thru Perplexity by the to sanitize it). PR reviews, would be fine if repo is private.
I feel this is overly exagerated here.
There is more issues that are currently getting leverage to hack with vscode extension than AI prompt injection, that require a VERY VERY complex chain of attack to get some leaks.
Re: Claude Code 2.0
#368FINALLY checkpoints! All around good changes, Claude Code is IMHO the best of the LLM CLI tools.
I already set up a jj (jujutsu) repo in my projects colocated with git (it uses git for its backend). Once you additionally set up a certain background daemon, it will then autocommit (label-lessly) every change to every file in that project. So you get "infinite undo", basically. It's actually more powerful than this checkpointing idea.
I'm a recent jj convert, and working with llms was actually a driver for my own jj adoption. I haven't tried the watch daemon, but I do run `jj new` anytime i ask the llm agent to do anything. It has worked amazingly well.
Re: Claude Code 2.0
#369I was already using jj (jujutsu) to do my own rewinds (it saves every change to every file as an unlabeled commit, assuming you set up its daemon). Would sort of prefer to continue to do that since it's far more flexible than checkpoints
How do you use jj to get those checkpoints? I was experimenting with jj and claude code, but it was frustrating to have it run jj status all the time, could as well tell it to do git commit all the time.
You don't need to run `jj status` all the time, but you DO need to have Watchman installed, and a config like this:
# ~/.jjconfig.toml
[core]
fsmonitor = "watchman"
[core.watchman]
# Newer docs use the hyphenated key below:
register-snapshot-trigger = trueRe: Claude Code 2.0
#370Earlier quoted context omitted.
You've been safe since launch because you haven't faced an adversarial prompt injection attack yet. You (and many, many others) likely won't take this threat seriously until adversarial attacks become common. Right now, outside of security researcher proof of concepts, they're still vanishingly rare. You ask why I'm obsessed with the danger? That's because I've been tracking prompt injection - and our total failure t…
how are you going to get "adversarial attacks" with prompt injection. If you don't fetch data from external sources. Web scraping ( you can channel that thru Perplexity by the to sanitize it). PR reviews, would be fine if repo is private. I feel this is overly exagerated here. There is more issues that are currently getting leverage to hack with vscode extension than AI prompt injection, that require a VERY VERY comp…
> how are you going to get "adversarial attacks" with prompt injection
Lots of ways his could happen. To name two: Third-party software dependencies, HTTP requests for documentation (if your agent queries the Internet for information).
If you don't believe me, setup a MITM proxy to watch network requests and ask your AI agent to implement PASETO in your favorite programming language, and see if it queries https://github.com/paseto-standard/paseto-spec at all.