This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Diogo de Lucena
Chief Scientist at AE Studio
Posts
Sorted by New
28
Mistral Large 2 (123B) exhibits alignment faking
1mo
0
31
Reducing LLM deception at scale with self-other overlap fine-tuning
1mo
9
20
Self-prediction acts as an emergent regularizer
6mo
0
56
Self-Other Overlap: A Neglected Approach to AI Alignment
9mo
7
Wikitag Contributions
Comments
Sorted by
Newest