you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 6 months ago (1 child)

The models themselves are actually entirely deterministic. The non-determinism you see is actually artificially introduced at the application layer to make the output seem more human. It's usually controlled by a setting called "heat", which when set to 0 will give completely reproducible results.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 3 points 6 months ago

    This is correct, I suppose you're talking about the final softmax layer? When I said they are bad at determinism, I was talking about reasoning on deterministic rules not having deterministic output. For example, LLMs make logical deduction errors, calculation errors etc.

  • source
  • parent