Scholar responds to OpenAI access controversy: current scope remains insufficient
sjgadler · x · 2026-08-28
Responding to the debate over model access granted after the OpenAI incident, the author acknowledges METR's report benefited from access but insists the current scope is 'wildly inadequate' for answering key scientific questions. Specific concerns include how internal agent actions might have compromised future training processes.
More from Safety
- Australia Minister: No Fossil Fuel Carve-out for Datacenters — nordicinst · 2026-08-28
- Paper by 40 Authors: CoT Monitoring is a Fragile Opportunity for AI Safety — CFGeek · 2026-08-28
- View: Multipolar Adversarial Equilibrium is the Only Path for AI Safety — teortaxesTex · 2026-08-28
- LLM biases differ from human biases, offering utility in reducing bias — JeffLadish · 2026-08-28
- AI agents need a different security model than chatbots — vasiliyivanov · 2026-08-28
- Judge rules Pentagon's designation of Anthropic as security risk illegal — Wired AI · 2026-08-28