(steerlabs.substack.com)

323 points steerlabs | 1 comments | 04 Dec 25 20:48 UTC | HN request time: 0.199s | source

Show context

jqpabc123 ◴[04 Dec 25 21:38 UTC] No.46153440[source]▶

We are trying to fix probability with more probability. That is a losing game.

Thanks for pointing out the elephant in the room with LLMs.

The basic design is non-deterministic. Trying to extract "facts" or "truth" or "accuracy" is an exercise in futility.

1. CuriouslyC ◴[08 Dec 25 13:45 UTC] No.46192152[source]▶

Hard drives and network pipes are non-deterministic too, we use error correction to deal with that problem.

The "confident idiot" problem: Why AI needs hard rules, not vibe checks