🧩 Philosophy 5h ago · Against Moloch

Quick Thoughts About Mythos

Less Wrong
View Channel →
Quick Thoughts About Mythos
Source ↗ 👁 1 💬 0
I expect it’ll take another week or two for everyone to fully digest the significance of Claude Mythos Preview. In the meantime, here are my initial thoughts.Gradually, then suddenlyMythos is radically better at cyber than any previous model:It isn’t the first model that can find vulnerabilities, of course: over the last several months we’ve seen a sharp increase in the rate of AI-discovered vulnerabilities.But Mythos is something new: it’s radically better not only at finding vulnerabilities at

Comments (0)

Sign in to join the discussion

More Like This

📰
Claude Interviews Me About Writing
LessWrong · 1h ago
An apple picking model for AI R&D
LessWrong · 2h ago
📰
Small models also found the vulnerabilities that Mythos found
LessWrong · 3h ago
📰
Catching illicit distributed training operations during an AI pause
LessWrong · 3h ago
📰
Dreams of the Future
LessWrong · 4h ago
Proof Explained: Touchette-Lloyd Theorem
LessWrong · 4h ago