Robert Wiblin questions OpenAI on dropping CoT monitoring with no replacement
AaronBergman18 · x · 2026-09-04
Robert Wiblin presses OpenAI on its apparent position: chain-of-thought monitorability is imperfect and won't last forever, so the company is reducing reliance on it — while currently replacing it with nothing, leaving a monitoring gap.
More from Safety
- WhatsApp Hid Instructions in Help Pages Telling Its AI Chatbot Not to Recommend Privacy Regulators — evilsocket · 2026-10-20
- Ex-OpenAI policy chief blasts OpenAI's retreat from AI chip controls to appease Nvidia — Miles_Brundage · 2026-10-20
- Time for Guardrails on Government Too: Rethinking Who AI Policy Constrains — neil_chilson · 2026-10-20
- MCP tool-poisoning detector broken in a day—here's the context-aware fix and what it still misses — blitzcrieg11 · 2026-10-20
- Argument-level permission rules for MCP tools: tool-name allowlists aren't enough — radim11 · 2026-10-20
- Layered defense for Text-to-SQL: prompt rules, validator, read-only connection — ZtasnimS75 · 2026-10-20