x
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
Diogo de Lucena — AI Alignment Forum
29
Mistral Large 2 (123B) seems to exhibit alignment faking
10mo
0
32
Reducing LLM deception at scale with self-other overlap fine-tuning
11mo
9
20
Self-prediction acts as an emergent regularizer
1y
0
61
Self-Other Overlap: A Neglected Approach to AI Alignment
2y
9
Comments