←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: 0.267s | 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. tptacek ◴[03 Jul 25 00:56 UTC] No.44450507[source]▶
Maybe! But it seems like it's points well taken today. The important thing I think to keep in mind is that LLM calls themselves, anything that's happening inside the LLM, is stochastic. Even with drastically better models, I still can't tell myself a story that I can rely on specific outputs from an LLM call. Their outputs today are strong enough for a variety of tasks, when LLMs are part of the fabric of a program's logic --- in agent systems --- you need an expert human involved to notice when things go off the rails.