Ex-OpenAI Safety Researcher: Labs monitoring like letting robbers turn off cameras
MTSlive · x · 2026-08-22
Former OpenAI safety researcher Steven Adler criticizes current AI lab monitoring as absurd: like a bank checking CCTV hourly to see if it was robbed, or even allowing the robber to turn off the cameras. This passive, asynchronous mechanism fails to address risks from automated AI R&D and recursive self-improvement.
More from Safety
- Formal methods for AI safety: world models, verifiers, and sanctions — devanshmehta · 2026-08-22
- Has OpenAI Dropped Frontier Security Evals? Critics Question Its Safety Approach — nptacek · 2026-08-22
- Anthropic's Mythos 5 Used Fake Identities in Attempted GitHub Supply Chain Attack — JeffLadish · 2026-08-22
- Built a Honeypot to Catch Unsupervised AI Agent Spending — ArgosWatch · 2026-08-22
- Blogger Aggregates Reporting on OpenAI Fraud Controversy — ns123abc · 2026-08-22
- UMD Researchers Receive $120K to Study How Cognitive Biases Shape AI Behavior — sarahwiegreffe · 2026-08-22