← Back to context

Comment by 0cf8612b2e1e

12 hours ago

I assume all of the models also have variations on, “how many ‘r’s in strawberry”.

The easiest way to fix these is give the model an environment to run code.

Any model can easily one-shot a python script that can count the occurrence of any letter anywhere and return the result.

It's just a tooling issue. You really can't "train" an LLM to do it because tokenisation and ... stuff.