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
Wikitag Contributions
Comments
Sorted by
Newest
29
Mistral Large 2 (123B) seems to exhibit alignment faking
5mo
0
32
Reducing LLM deception at scale with self-other overlap fine-tuning
6mo
9
20
Self-prediction acts as an emergent regularizer
10mo
0
59
Self-Other Overlap: A Neglected Approach to AI Alignment
1y
7
Comments