←back to thread

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

(steerlabs.substack.com)
323 points steerlabs | 1 comments | 04 Dec 25 20:48 UTC | HN request time: 0s | 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.

replies(17): >>46155764 #>>46191721 #>>46191867 #>>46191871 #>>46191893 #>>46191910 #>>46191973 #>>46191987 #>>46192152 #>>46192471 #>>46192526 #>>46192557 #>>46192939 #>>46193456 #>>46194206 #>>46194503 #>>46194518 #
hbs18 ◴[08 Dec 25 14:59 UTC] No.46192939[source]▶
> The basic design is non-deterministic

Is it? I thought an LLM was deterministic provided you run the exact same query on exact same hardware at a temperature of 0.

replies(2): >>46193272 #>>46194041 #
1. biophysboy ◴[08 Dec 25 16:13 UTC] No.46194041[source]▶
My understanding is that it selects from a probability distribution. Raising the temperature merely flattens that distribution, Boltzmann factor style