Author

Kevin Baum

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best

This account unifies alignment faking, sandbagging, and evaluation-aware scheming and reorients the remedy: not deeper internalization but architecture, making violations unavailable rather than unchosen.

Kevin Baum, R. Binkytė, Felix Jahn · 0 citations