I suspect even typos have an impact on how the model functions.
I wonder if there’s a pre-processor that runs to remove typos before processing. If not, that feels like a space that could be worked on more thoroughly.
there is no pre-processor, i've had typos go through, with claude asking to make sure i meant one thing instead of the other
I guess just a spell-check in the repo? But yes, I'd imagine that they have an effect. Even running the same input twice is non-deterministic.