News for hackers. Stuff that matters.

A comment on Flow-Based Programming, a way for AI and humans to develop together. Parent comment

Re:Flow-Based Programming, a way for AI and humans to develo... by ethanwillis on Monday March 20, 2023 @07:22AM (#35229990)
On your first point you couldn't be more wrong. LLMs are deterministic. They are run on a deterministic machine and the entailment of that forces them to be so. Also probabilistic does not mean the absence of determinism. For example, for every non-deterministic/probabilistic finite automata there is an equivalent deterministic one.
[ Parent | on HN ]
Re:Flow-Based Programming, a way for AI and humans to develo... by xyzzy123 on Monday March 20, 2023 @08:11AM (#35230383)
LLMs can be implemented to be formally deterministic but if you ask them to solve a specific problem instance you have not seen before, you cannot generally guarantee they will do so reliably. So you're correct in a pedantic sense but I think GP's perspective is more useful if you are problem solving.
[ Parent | on HN ]
Re:Flow-Based Programming, a way for AI and humans to develo... by ethanwillis on Monday March 20, 2023 @11:45PM (#35242323)
It's not pedantry. The parent commentator is simply stating something incorrect and its very misleading at a conceptual level for people who won't think about it too much. And you can guarantee they will do so reliably unless you parameterize the input with some "truly" (yea i know) random input.
[ Parent | on HN ]
Re:Flow-Based Programming, a way for AI and humans to develo... by hgsgm on Monday March 20, 2023 @09:29AM (#35231205)
You are arguing metaphysics but this conversation is about computer science.

In computer science, pseudorandomness is considered non-deterministic. Determinism is a function of the inputs, not the machine state.

https://en.m.wikipedia.org/wiki/Deterministic_algorithm#:~:t....

[ Parent | on HN ]
Re:Flow-Based Programming, a way for AI and humans to develo... by Aeolos on Monday March 20, 2023 @10:12AM (#35231776)
LLMs are fully deterministic in that sense: same input, same outputs.

Because full determinism is not always desirable, the researchers have implemented an explicit "temperature" parameter that you can use to inject randomness to the outputs. If you set that to 0.0 you will always receive the same output for the same input and model version.

[ Parent | on HN ]