Redwood Research(@redwood_ai):Some architectures could weaken CoT monitorability, or remove the CoT altogether. We've written a proposal for how companies could be transparent about no-CoT reasoning abilities, other monitorability evidence, and policies for preserving monitorability.

Redwood Research

@redwood_ai

Pioneering threat mitigation and assessment for AI agents.

参加 December 2024

6 フォロー中 4.9K ファン

Redwood Research@redwood_ai

2026.09.10 17:05

Some architectures could weaken CoT monitorability, or remove the CoT altogether. We've written a proposal for how companies could be transparent about no-CoT reasoning abilities, other monitorability evidence, and policies for preserving monitorability.