I’d argue repeatability is impossible to guarantee. Any cloud based computing with floating point math is subject to variance. Bare metal local LLM computing can be relatively stable, but still suffers from precision error from your GPU.

I think we’re on the same page with this, but agree to disagree on functional determinism being a semantic argument in the context of this thread.

Functionally non-deterministic if we compare the same input with outputs over a short enough period.

Deterministic if you have infinite time to run the gamut of model weights against temperature/creativity/programmed randomness, but even then maybe not if floating point math is taken into account. I don’t know where the current thought is on extreme precision being deterministic or not given cloud environments, local operating and environmental factors, variance in manufacturing, and the like.

@grok summarize this