[JacobAsmuth]

Have you read firefoxes findings? They found it to be qualitatively improved over Opus, and have published several of the resulting CVEs as well as more detailed numbers.

[bcrosby95]

They also seem to point to it being more the harness than the model itself.

[JacobAsmuth]

Really? They mention that Opus 4.7 in the same harness found like 1% of the bugs that Mythos found.