←back to thread

What to build instead of AI agents

(decodingml.substack.com)
233 points giuliomagnifico | 2 comments | 03 Jul 25 00:02 UTC | HN request time: 0.54s | source
Show context
dmezzetti ◴[03 Jul 25 00:59 UTC] No.44450535[source]▶
This article is missing an even more important point: you don't always need to start with an LLM, plain old coding still solves a lot of problems.
replies(2): >>44450609 #>>44451032 #
1. skeeter2020 ◴[03 Jul 25 02:25 UTC] No.44451032[source]▶
It's funny how when I talk to ML practitioners who have experience & work in the field they're the most pragmatic voices, like our staff developer on the ML team: "if you can solve the problem algorithmically you should definitely do that!"
replies(1): >>44453709 #
2. dmezzetti ◴[03 Jul 25 10:54 UTC] No.44453709[source]▶
For full disclosure, I work on txtai one of the more popular AI frameworks out there. So this checks out :)