[wat10000]

Determinism is predicated on what you consider to be the relevant inputs.

Many compilers are not deterministic when only considering the source files or even the current time. For example, any output produced by iterating over a hash table with pointer keys is likely to depend on ASLR and thus be nondetermistic unless you consider the ASLR randomization to be one of the inputs. Any output that depends on directory iteration order is likely to be consistent on a single computer but vary across computers.

LLMs aren’t magic. They’re software running on inputs like anything else, which means they’re deterministic if you constrain all the inputs.

[kiitos]

LLMs are 100% absolutely not deterministic even if you constrain all of their inputs. This is obviously the case, apparent from any even cursory experimentation with any LLM available today. Equivocating the determinism of a compiler given some source code as input, with the determinism of an LLM given some user prompt as input, is disingenuous to the extreme!

[wat10000]

Most LLM software isn’t deterministic, sure. But LLMs are just doing a bunch of arithmetic. They can be 100% deterministic if you want them to be.

[kiitos]

In practice, they definitely are not.

[wat10000]

Only because nobody cares to. Just like compilers were not deterministic in practice until reproducible builds started getting attention.