News for hackers. Stuff that matters.
Re:AI cybersecurity is not proof of work by mbesto on Thursday April 16, 2026 @12:45PM (#47796092)
And overfitting benchmarks can easily be gamed. Yet here we are with the top HN comment on the HN Mythos thread outlining it's benchmarking performance gains.

I guess we'll never learn.

There are no comments on this comment yet.