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.
More from AGI Musings
- When AI can clone your product by sight, paid software's moat is service and trust — sujingshen · 2026-10-18
- Anthropic borrows lawyers' ethics for Claude agents that closed 186 deals with no human approval — rohanpaul_ai · 2026-10-18
- Tim Sweeney: AI will unlock a new golden age of games too costly to build before — TinfoilTricorn · 2026-10-18
- Researcher argues we may solve AI-human alignment before humans align with each other — 3scorciav · 2026-10-18
- EigenGender: private-industry coup isn't the default, but worth guarding against — EigenGender · 2026-10-18
- Writing instructor's meltdown: "LLMs are literally just spicy autocomplete" — Decent-Decision-9028 · 2026-10-18