News for hackers. Stuff that matters.
Re:Project Glasswing: what Mythos showed us by meander_water on Monday May 18, 2026 @05:25PM (#48185886)
> the model has its own emergent guardrails that sometimes cause it to push back on legitimate security research requests. But as we found, these organic refusals aren’t consistent - the same task, framed differently or presented in a different context, could produce completely different outcomes as illustrated in the examples below.

This was new. I'm surprised that a model specifically designed for security research and gated to professionals is refusing legitimate requests

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.
Re:Project Glasswing: what Mythos showed us by sn0rl27 on Tuesday May 19, 2026 @02:14PM (#48197061)
The model wasn’t created specifically for security research. It’s a general model that just happens to be dangerously good at security research (according to Anthropic)