News for hackers. Stuff that matters.
Re:Coding agent in 94 lines of Ruby by tough on Friday May 16, 2025 @08:12PM (#44010942)
> What makes something a good potential tool, if the shell command can (technically) can do anything - like running tests?

Think of it as -semantic- wrappers so the LLM can -decide- what action to take at any given moment given its context, the user prompt, and available tools names and descriptions.

creating wrappers for the most used basic tools even if they all pipe to terminal unix commands can be useful.

also giving it speicif knowledge base it can consult on demand like a wiki of its own stack etc

Re:Coding agent in 94 lines of Ruby by notpushkin on Friday May 16, 2025 @08:52PM (#44011175)
Also it’s safer than just giving unrestricted shell access to an LLM.
Re:Coding agent in 94 lines of Ruby by tough on Saturday May 17, 2025 @11:58AM (#44015197)
that too, ideally autonomous agents will be only spawnrd in their own secure environments using docker or vm’s or posix / unix security

but yeah