Remember though that many other AIs had already run and found issues that were fixed. If you had a time machine and took Mythos back a year it probably would have found a lot more. (if anyone has access to mythos it wouldn't be hard to test - download a release from last year and check)

> if anyone has access to mythos it wouldn't be hard to test - download a release from last year and check

Mythos might have seen last years bug reports so that might be cheating, kind-of. Bug reports ought to be great study material for LLM training.

Imagine the bugs you'd find in curl from five years ago! I bet there are tons!