Anthropic says Fable 5 has invisible safeguards that use prompt modification, steering vectors, or PEFT to limit its effectiveness for building frontier LLMs (Matthias Bastian/The Decoder)
Matthias Bastian / The Decoder: Anthropic says Fable 5 has invisible safeguards that use prompt modification, steering vectors, or PEFT to limit its effectiveness for building frontier LLMs — Key Poin