[phyalow]

“non-deterministic machines“

Not correct. They are deterministic as long as a static seed is used.

[kazga]

That's not true in practice. Floating point arithmetic is not commutative due to rounding errors, and the parallel operations introduce non-determinisn even at temperature 0.

[SetTheorist]

Nitpick: I think you mean that FP arithmetic is not _associative_ rather than non-commutative.

Commutative: A+B = B+A Associative: A+(B+C) = (A+B)+C

[zorked]

That's basically a bug though, not an important characteristic of the system. Engineering tradeoff, not math.

[phyalow]

What? You can get consistent output on local models.

I can train large nets deterministically too (CUBLAS flags). What your saying isn't true in practice. Hell I can also go on the anthropic API right now and get verbatim static results.