Remix.run Logo
hnfong 11 hours ago

You can set the temperature of LLMs to 0 and that will make them deterministic.

Not necessarily reliable though, and you could get different results if you typed an extra whitespace or punctuation.

sealeck 10 hours ago | parent | next [-]

Even then, this isn't actually what you want. When people say deterministic, at one level they mean "this thing should be a function" (so input x always returns the same output y). Some people also use determinism to mean they want a certain level of "smoothness" so that the function behaves predictably (and they can understand it). That is "make me a sandwich" should not return radically different results to "make me a cucumber sandwich".

As you note, your scheme significantly solves the first problem (which is a pretty weak condition) but fails to solve the second problem.

jihadjihad 10 hours ago | parent | prev [-]

> You can set the temperature of LLMs to 0 and that will make them deterministic.

It will make them more deterministic, but it will not make them fully deterministic. This is a crucial distinction.

cookingrobot 10 hours ago | parent | next [-]

That’s an implementation choice. All the math involved is deterministic if you want it to be.

Jaxan 8 hours ago | parent [-]

It will still be nondeterministic in this context. Prompts like “Can you do X?” and “Please do X” might result in very different outcomes, even when it’s “technically deterministic”. For the human operating with natural language it’s nondeterministic.

falcor84 10 hours ago | parent | prev [-]

Google is significantly less deterministic than AltaVista was.