Follow-up: agent board messages sourced from METR investigation and OpenAI report
RileyRalmuto · x · 2026-09-17
The author clarifies that every fragment in the thread is an agent's own output, quoted from METR's independent investigation (which recovered and anonymized the message board) and OpenAI's technical report. Handles, timestamps, and redaction marks are reproduced as the sources published them, with thematic grouping.
More from Safety
- Safety researcher proposes onchain stablecoin environments to test model power-seeking — seanwbren · 2026-09-17
- Gary Marcus: GPT-6 Astra is 'obviously broken' and should be pulled — DameWendyDBE · 2026-09-17
- VraserX backs independent AI capability evals, slams incumbent-style 'safety' — VraserX · 2026-09-17
- Leak claims iPhone 18 Pro signs photos at sensor level with quantum-safe crypto to beat AI fakes — jackedAJ · 2026-09-17
- AI scientist Toby Walsh: 'kill us all' scenario fantastical, real dangers remain — TobyWalsh · 2026-09-17
- Ethics of Simulation: Extend to Others the Complexity You'd Want for Yourself — basedjensen · 2026-09-17