|
|
|
|
|
|
by clbrmbr
69 days ago
|
|
|
There’s also a paper [0] from many well known researchers that serves as a kind of informal agreement not to make the CoT unmonitorable via RL or neuralese. I also don’t think Anthropic researchers would break this “contract”. [0] https://arxiv.org/abs/2507.11473 |
|
|