OpenAI Staff: Frontier Model Computation Depth Close to GPT-4

__nmca__ · x · 2026-09-02

An OpenAI employee clarified that the depth of the computation graph for current frontier models, including Astra, is within a factor of two of GPT-4, countering reports of unmonitorability. They emphasized that OpenAI has worked to preserve and utilize chain-of-thought monitoring since their first reasoning models, viewing it as crucial for visibility into model alignment.

Related event: OpenAI Researchers Push Back on Neuralese Fears: Frontier Models Remain Monitorable(11 posts)→

Original post →

More from Safety

Safety channel →