Comment by lionkor
3 hours ago
LLMs are not another abstraction. ALL OTHER LAYERS you named are fully deterministic, understood, debuggable, etc.
You cannot be serious.
3 hours ago
LLMs are not another abstraction. ALL OTHER LAYERS you named are fully deterministic, understood, debuggable, etc.
You cannot be serious.
LLMs are one of the most general abstractions possible.
LLMs are also quite deterministic if you want them to be - generally, their final token selection is deliberately randomized (the model “temperature”). But the word you’re looking for here is probably not actually determinism, it’s probably something closer to predictability.
In any case, it’s perfectly possible to ensure that the output of LLMs is fully deterministic, debuggable, understandable, and testable.
> You cannot be serious.
I don’t think you’re thinking about this clearly.