Re:We no longer use LangChain for building our AI agents
by CGamesPlay on Friday June 21, 2024 @02:23AM
(#40746732)
Fundamentally, "Agent" refers to anything that operates in an "observe-act" loop. So in the context of LLMs, an agent sees an observation (like the code base and test output) and produces an action (like a patch), and repeats.
[ Parent
| on HN ]
There are no comments on this comment yet.