Re:Claude 4.5 Opus' Soul Document
by Sol- on Tuesday December 02, 2025 @03:53PM
(#46126704)
No, I think apparently it was used in the reinforcement learning step somehow to influence the model's final fine-tuning. At least how I understood it.
The actual system prompt from Anthropic is shorter and also public on their website I believe
The actual system prompt from Anthropic is shorter and also public on their website I believe