logoalt Hacker News

throwa356262yesterday at 9:29 AM1 replyview on HN

I really like this!

Claude Code always resorts to running small python scripts to test ideas when it gets stuck.

Something like this would mean I dont need to approve every single experiment it performs.


Replies

stingraycharlesyesterday at 9:31 AM

Didn’t Anthropic recently acquire some JavaScript engine, though?

I figured that that was because they want tighter integration and a safer execution environment for code written by the LLM. And sandboxing is already very common for JavaScript in browsers.