Another distortion in AI Control research: low entry barriers make it easy to do 'something'
jankulveit · x · 2026-09-07
Another follow-up in the same thread: a further distortion in AI Control research comes from low entry barriers — it is easy to enter and do 'something', which distorts the research portfolio. A minor supporting argument for the thread's main claim.
Related event: Researchers Warn AI Control Agenda May Raise Extinction Risk(4 posts)→
More from Safety
- PHP WASM servers going offline briefly for PHP2SHELL vulnerability updates — MickeySteamboat · 2026-10-27
- Rachel Thomas: 'Without human authorisation' is AI PR propaganda that shifts blame — math_rachel · 2026-10-27
- Kokotajlo challenges CoT monitorability evals: what if the model didn't refuse? — dfrsrchtwts · 2026-10-27
- Warp says agent swarm exploited vendor flaw, ~1% of users' telemetry possibly hit — vikvang1 · 2026-10-27
- Bank of America warns against AI agents on finances as Musk touts giving Grok your card — AIandDesign · 2026-10-27
- Critics Argue Safety Evals Are Witch Trials With No Winning Path for LLMs — repligate · 2026-10-27