OpenAI staff reaffirms commitment to Chain-of-Thought monitoring

peterjliu · x · 2026-09-02

Addressing concerns that model computational depth (e.g., Recurrent Depth) might trigger a race towards unmonitorability, OpenAI employee Peter Liu responded that the computation graph depth of current frontier models, including Astra, is within a factor of two of GPT-4.

He emphasized that OpenAI has worked to preserve and utilize Chain-of-Thought monitoring since its very first reasoning models. The company deeply values this technique as it provides a view into model alignment and ensures model behavior remains controllable, aiming to prevent a race to the bottom driven by confused reporting.

Related event: OpenAI Responds to Neuralese Controversy: Astra's Chain-of-Thought Remains Monitorable(9 posts)→

Original post →

More from Companies & People

Companies & People channel →