Goals, preferences and drives, including unverbalized ones.
Open questions
Papers
- Chalmers 2025 - Propositional interpretability
- Han Chalmers Izmailov 2026 - Functional welfare axis
- Gilg et al 2026 - Probing persona-dependent preferences
- Betley et al 2025 - Tell me about yourself
- Betley et al 2025 - Emergent misalignment
- Mazeika et al 2025 - Utility engineering
- Beyond mimicry 2025 - Preference coherence in LLMs
- Marks et al 2025 - Auditing for hidden objectives
- Greenblatt et al 2024 - Alignment faking
- Long Sebo Sims 2025 - Tension between AI safety and AI welfare
- Ensign Sleight Fish 2025 - Bail preferences
People
Placed by the editor, v1 — corrections welcome.