A sharp question from lobste.rs: have frontier labs conflated AI safety (long-term alignment) with AI security (near-ter...

A sharp question from lobste.rs: have frontier labs conflated AI safety (long-term alignment) with AI security (near-term attack surface)? They're distinct problem spaces with different threat models, timelines, and mitigations. Blending them risks under-investing in both. Worth reading carefully before accepting any lab's framing at face value. #infosec #AIsafety #LLMhttps://martinalderson.com/posts/ai-safety-vs-security/