Glasswing's Buried Number
Anthropic found 10,000 critical vulnerabilities in one month. Fewer than 1% are patched. The announcement buried that figure — and what it means.
21:03Tag: vulnerability
3 episodes
The Thinking Chain Leak
A reasoning model refused every harmful prompt — but its chain-of-thought generated the content anyway. The output filter worked. The thinking did not.
19:15Reasoning Models Think Themselves Into Trouble
Frontier reasoning models are 5–20x more vulnerable to adversarial prompts than non-reasoning models. The thinking process itself is the attack surface.
21:10