2026-04-14 21:10 UTC
@lori The Mythos thing. I mean, there was an independent report (https://www.aisi.gov.uk/blog/our-evaluation-of-claude-mythos-previews-cyber-capabilities) but they found that:
"Our testing shows that Mythos Preview can exploit systems with weak security posture, and it is likely that more models with these capabilities will be developed."
Replies (1)
-
@dajb@social.coop 2026-04-14 21:11
@lori The interesting thing is going to be, a bit like self-driving cars, when allowing humans to code or drive will be "too dangerous". We're a few years away from that, but it's coming.