Ask HN: AI agent devs, how do you sandbox LLM generated code?

Sometime we need to execute LLM generated code from within our app. For that we are using VMs today, but it's slow. How are others handling this?

6 points | by ATechGuy 1 day ago

5 comments

lunarcave 9 hours ago
There are a few tools here like e2b and modal. No affiliation.
[1] https://e2b.dev [2] https://modal.com
I’m in the same space, but we run the code that devs already write using LLMs to orchestrate them.
vdvsvwvwvwvwv 22 hours ago
AWS Lambdas?
meiraleal 20 hours ago
iframes
osipov 1 day ago
[dead]