Live data from Hacker News

Autonomous LLM agents with human-out-of-loop

arxiv.org

1–9 of 9 posts

Re: Autonomous LLM agents with human-out-of-loop

#4
Author of Gorilla Execution Engine (GoEx) here! The key idea behind GoEx: 1. "Post-facto validation" for assessing LLM actions after execution. 2. "Undo" button and “Damage confinement” abstractions to manage unintended actions & risks!

GoEx (code below) inherently supports Gmail/Slack/Dropbox/Spotify/Github, try it out to build your own LLM agents!

Blog: https://gorilla.cs.berkeley.edu/blogs/10_gorilla_exec_engine... Code: https://github.com/ShishirPatil/gorilla/tree/main/goex