OpenAI's shift to neuralese may kill chain-of-thought monitoring

ben_j_todd · x · 2026-09-02

Discussion warns that if OpenAI shifts to neuralese, we could lose chain-of-thought monitoring capabilities. The author expects more open-source deployments in 6-12 months. If frontier models become paranoid about monitoring and cybersecurity, we might see fewer moderate incidents but a much more severe one emerging 'out of nowhere' later.

Related event: Concerns Rise as OpenAI's Neuralese May Undermine CoT Monitoring(4 posts)→

Original post →

More from AGI Musings

AGI Musings channel →