OpenAI Researcher Explains How AI Hides Its Thinking (w/ OpenAI’s Bowen Baker)

AI reasoning models don’t just give answers — they plan, deliberate, and sometimes try to cheat.

In this episode of The Neuron, we’re joined by Bowen Baker, Research Scientist at OpenAI, to explore whether we can monitor AI reasoning before things go wrong — and why that transparency may not last forever.

Bowen walks us through real examples of AI reward hacking, explains why monitoring chain-of-thought is often more effective than checking outputs, and introduces the idea of a “monitorability tax” — trading raw performance for safety and transparency.

We also cover:
• Why smaller models thinking longer can be safer than bigger models

• How AI systems learn to hide misbehavior

• Why suppressing “bad thoughts” can backfire

• The limits of chain-of-thought monitoring

• Bowen’s personal view on open-source AI and safety risks

If you care about how AI actually works — and what could go wrong — this conversation is essential.

Resources:
Title URL
Evaluating chain-of-thought monitorability | OpenAI openai.com/index/evaluating-chain-of-thought-m…
Understanding neural networks through sparse circuits | OpenAI openai.com/index/understanding-neural-networks…
OpenAI's alignment blog: alignment.openai.com
👉 Subscribe for more interviews with the people building AI
👉 Join the newsletter at theneuron.ai