Tag: ai-safety
All the articles with the tag "ai-safety".
-
Claude Fable 5 / Mythos 5 System Card: What's Actually Inside, and Why It Reads Like Sci-Fi
Flipping through the Claude Fable 5 and Mythos 5 system cards: stealing keys, office politics, AI infighting, gibberish, and a two-faced model. The more I read, the more it feels like a straight-faced sci-fi novel.
-
Judging AI Risk on Two Axes: Reversibility × Environment Isolation
A common question in corporate trainings — "can I let AI do this automatically?" I answer with two axes: reversible vs irreversible, isolated vs production. This 2x2 prevents more incidents than any prompt-engineering tutorial.