←back to thread

What to build instead of AI agents

(decodingml.substack.com)
233 points giuliomagnifico | 1 comments | 03 Jul 25 00:02 UTC | HN request time: 0s | source
Show context
ldjkfkdsjnv ◴[03 Jul 25 00:49 UTC] No.44450452[source]▶
This is all going to be solved by better models. Building agents is building for a world that doesn't quite exist yet, but probably will in a year or two. Building some big heuristic engine that strings together LLM calls (which is what this blog advocates for) is essentially a bet against progress in ai. I'm not taking that bet, and neither are any of the major players.
replies(7): >>44450462 #>>44450475 #>>44450503 #>>44450507 #>>44450563 #>>44450783 #>>44452156 #
1. snek_case ◴[03 Jul 25 00:52 UTC] No.44450475[source]▶
I've been reviewing papers for NeurIPS and I can tell you that many of the submissions are using various strategies to string together LLM calls for various purposes.

It tends to work better when you give the LLMs some specific narrow subtask to do rather than expecting them to be in the driver's seat.