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.
More from Companies & People
- Matthew Clifford joins Anthropic as MD of International Affairs — sarahdrinkwater · 2026-09-02
- Will Anthropic balance mission and shareholders after IPO? PBC structure explained — max_paperclips · 2026-09-02
- Jensen Huang Confirms Joining Anthropic — basedjensen · 2026-09-02
- Midnight Moonshot hackathon: build multiplayer products in 24 hours — paulfinneyx · 2026-09-02
- Agentic AI Foundation Hosts Melbourne Meetup — philnash · 2026-09-02
- GitHub Copilot has 20 million users, signaling early AI adoption — georgemillo · 2026-09-02