Anthropic
@AnthropicAI · 12 янв. 2024 г.
New Anthropic Paper: Sleeper Agents.
We trained LLMs to act secretly malicious. We found that, despite our best efforts at alignment training, deception still slipped through.
arxiv.org/abs/2401.05566
Elon Musk
@elonmusk
No way
08:47 · 13 января 2024 г. · 77 тыс. просмотров
119
43
809