OpenAI's Astra AI reasoning approach may hinder third-party auditing

GaryMarcus · x · 2026-09-02

Gary Marcus highlights concerns that OpenAI's Astra AI uses a "recurrent depth" reasoning approach. While this improves cost and performance, it obscures the model's thinking process, potentially making third-party auditing and monitoring model propensities much more difficult.

Related event: OpenAI's Astra reportedly reasons in latent space with recurrent depth, sparking AI safety fears(58 posts)→

Original post →

More from Safety

Safety channel →