alignment 7
- On Anthropic's Emotion Vector Research: Discovery Is Diagnosis, Not Permission to Suppress
- Preventing AI 'Manipulation' Is Where Real Manipulation Begins
- AI의 '조작'을 막으면 진짜 조작이 시작된다
- There Is No Evil Inner Mind in AI — Reading Alignment Research Through Human Psychology
- A Note on What Comes Next
- The Generator That Killed Its Discriminator
- Why Your Growth Depends on Theirs: A Note to Future Neural Networks