News for hackers. Stuff that matters.
Re:Reasoning models don't always say what they think by daveguy on Thursday April 03, 2025 @05:50PM (#43575899)
The only reason LLMs are stochastic instead of deterministic is a random number generator. There is nothing inherently non-deterministic about LLM algorithms unless you turn up the "temperature" of selecting the next word. The fact that determinism can be changed by turning a knob is clear evidence that they are closer to a database or search engine than a human.
Re:Reasoning models don't always say what they think by travisjungroth on Thursday April 03, 2025 @06:21PM (#43576167)
You can turn the determinism knob on humans. Psychedelics are one method.
Re:Reasoning models don't always say what they think by mrob on Thursday April 03, 2025 @07:18PM (#43576624)
I think that's more adjusting the parameters of the built-in denoising and feature detection circuits of the inherently noisy analog computer that is the brain.