401–410 of 431 posts
You have to specify `/model sonnet[1m]` to get the 1 million context version
Be careful. exceeding around the original 200k tokens leads to worse and worse results. It's important to have context clean and tailored to the current task.
[0] https://cognition.ai/blog/devin-sonnet-4-5-lessons-and-chall...
Earlier quoted context omitted.
Wow, could you expand on this? What kind of effects can you get out of it? I’m somewhat skeptical that this could even come close to a proper mastering chain, so I’d be extremely interested to learn more :)
Any effect you can imagine. It could probably write a DAW if you wanted it to, but a “one-off” script? Easy. I think the best thing is when I tell it something like “it sounds like there is clipping around the 1:03 mark” it will analyze it, find the sign flip in the processor chain, and apply the fix. It’s much faster at this than me. Note that there needs to be open source libraries and toolings. It can’t do a Dolby…
Earlier 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…
https://gitlab.com/txlab/ai/sandcastle/
Check it out if you're experimental - but probably better in a few weeks when it's more stable.
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.
You can find the revamped prompt on github[1], or on twitter summarized by my bot[2]. [1] https://github.com/marckrenn/cc-mvp-prompts/compare/v1.0.128... [2] https://x.com/CCpromptChanges/status/1972709093874757976
I should probably include that in my Claude.md instead I guess?
Earlier quoted context omitted.
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-...
Not specific to LLM stuff, but I've lately been using bubblewrap more and more to isolate bits of software that are somewhat more sketchy (NPM stuff, binaries downloaded from GitHub, honestly most things not distro-packaged). It was a little rocky start out with, but it is nice knowing that a random binary can't snoop on and exfiltrate e.g. my shell history.
Earlier quoted context omitted.
How are you extracting this - aren’t the main labs obfuscating these (meaning it’s likely to be a decoy or incomplete version)?
With cchistory https://github.com/badlogic/cchistory Here's how it works: https://mariozechner.at/posts/2025-08-03-cchistory/
Earlier quoted context omitted.
From the docs it looks like this feature only reverts the edit tool calls, and not e.g. bash commands that have been executed: > Checkpoints apply to Claude’s edits and not user edits or bash commands, and we recommend using them in combination with version control
How could they possibly hope to undo bash commands, whose side effects could be anything, anywhere? Hey Claude... uh... unlaunch those
Earlier quoted context omitted.
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.
https://news.ycombinator.com/item?id=45426787
Avoids even having to do "jj new"!
Earlier quoted context omitted.
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.
I automated that with some simple claude hooks that detect if we're in a `jj` repo and also prompts claude to `jj commit -m` after every change.
https://news.ycombinator.com/item?id=45426787
Avoids having to do any jj command at all!