We asked AI agents to fix real security bugs. This is what happened (mobb.ai) 1 points by k1r111 10d ago ↗ HN
[–] root-parent 10d ago ↗ TLDR;Vendors are gaming the benchmarks, self reporting, and Mythos is probably not as good as they want you to believe.
3 comments
[ 3.4 ms ] story [ 18.6 ms ] threadVendors are gaming the benchmarks, self reporting, and Mythos is probably not as good as they want you to believe.