Selection Pressures on LM Personas
Raymond Douglas — 2025-03-28
Source
- Link: https://www.lesswrong.com/posts/LdBhgAhpvbdEep79F/selection-pressures-on-lm-personas
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- character-training-and-persona-steering — Black-box safety (understand and control current model behaviour) / Model psychology