Re:Project Glasswing: what Mythos showed us
by _alternator_ on Monday May 18, 2026 @06:40PM
(#48186795)
There's pretty strong evidence that (mis)alignment in one area creates (mis)alignment in others. The "aligned behavior" vectors are not orthogonal from cybersecurity to bioweapons to prejudice, so having alignment in some will likely bleed into others.
This was new. I'm surprised that a model specifically designed for security research and gated to professionals is refusing legitimate requests