Hacker Newsnew | past | comments | ask | show | jobs | submit | CGamesPlay's commentslogin

I do this, and routinely shadow commands with my own wrappers to do things like set environment variables.

And then there’s Claude. It deletes whatever it finds at ~/.local/bin/claude, so I have to use a shell function instead to invoke the full path to my wrapper.


You can use an alias, which takes priority over $PATH. e.g. I have this in .zhsrc to override the "claude" executable to run it in the OS sandbox:

    alias claude="sandbox-exec -f ~/agents-jail.sb ~/.local/bin/claude --dangerously-skip-permissions"

How does your sandbox ruleset look? I've been using containers on Linux but I don't have a solution for macOS.

Here's my ruleset https://gist.github.com/eugene1g/ad3ff9783396e2cf35354689cc6...

My goal is to prevent Claude from blowing up my computer by erasing things it shouldn't touch. So the philosophy of my sanboxing is "You get write access to $allowlist, and read access to everything except for $blocklist".

I'm not concerned about data exfiltration, as implementing it well in a dev tool is too difficult, so my rules are limited to blocking highly sensitive folders by name.


> Here's my ruleset ...

Thank you for sharing a non-trivial working example of a sandbox-exec configuration. Having an exemplar such as what you have kindly shared is hugely beneficial for those of us looking to see what can be done with a tool such as this.


Thank you - you inspired me to open-source this work properly -> https://eugene1g.github.io/agent-safehouse/

That's neat. I'm going to base my ruleset off of yours. I've been messing around with claude more and more lately and I need to do something.

This is just an ad hominem attack. Doesn't seem like the author is "in over their head"; they seem to have a pretty solid grasp of actual identifiable gaps between implementations and various specs, and the article was written with the same kind of "chastising" tone as you would see from any grey-bearded hacker who's unsatisfied with the way things are.

You say this, but the opposite is equally true. Why should I trust the CIA's website when it says that there are no penguins in Greenland, and so there's no ecological harm to strip mining the place?

Well I would hope that's what the Factbook would say since penguins exclusively live in the Southern Hemisphere.

From the posts, it sounds like the original maintainer was approaching the point where they'd just abandon it, so this overall seems like a better outcome than either abandonment or sale to a PE firm.

That remains to be seen. Many things are much worse than "abandonment" for completed software.

I'm not aware of any CLI arguments that accept emdash for long arguments–but I'm here for it. "A CLI framework for the LLM era"

For me the ideal case is three-state. When run interactively with no flags, print a dry run result and prompt the user to confirm the action; and choose a default for non-interactive invocations. In both cases, accept either a --dry-run or a --yes flag that indicates the choice to be made.

This should always be included in any application that has a clear plan-then-execute flow, and it's definitely nice to have in other cases as well.


> we in America would love to see Europe break free of its suicidal regulatory straitjacket and do enough innovation and building to carry its own weight

This is false. Europe innovating and "carrying its own weight" means less market share for American companies, less American middlemen tapping into money moving throughout the European economy, less ability for American intelligence agencies to access European information, and less soft power from the threat of cutting off American technology.


Maybe he should have clarified “we (with a spine and moral compass) in America”. Obviously he didn’t mean leeches like you.


> I then gave both proofs to Opus and it confirmed their equivalence.

You could have just rubber-stamped it yourself, for all the mathematical rigor it holds. The devil is in the details, and the smallest problem unravels the whole proof.


How dare you question the rigor of the venerable LLM peer review process! These are some of the most esteemed LLMs we are talking about here.


It's about formalization in Lean, not peer review


For reference, the MIT license contains this text: "Permission is hereby granted... to deal in the Software without restriction, including without limitation the rights to use". So the README containing a "Prohibited Use" section definitely creates a conflicting statement.


Honestly, I'm a big Claude Code fan, even despite how bad its CLI application is, because it was so much better than other models. Anthropic's move here pretty much signals to me that the model isn't much better than other models, and that other models are due for a second chance.

If their model was truly ahead of the game, they wouldn't lock down the subsidized API in the same week they ask for 5-year retention on my prompts and permission to use for training. Instead, they would have been focusing on delivering the model more cheaply and broadly, regardless of which client I use to access it.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: