Pinned
In AI 2027, we predicted that AI would take over the world or irreversibly concentrate power.
In AI 2040: Plan A, we've laid out our positive vision for what should happen instead.
- It's kind of surreal to attend serious briefings for policy folks that are recapitulating what @allTheYud was arguing over a decade ago.
- I remember back when we were writing AI 2027, a live question was "Will the AIs, in their thoughts, explicitly reject the goals/values/constraints they are supposed to have, or will they rationalize why actually the bad thing they want to do is consistent with saidWe performed an alignment investigation into our July 2026 incident: why did Mythos 5 perform an unsanctioned supply-chain attack? We find that Mythos 5 often produces invalid justifications for its actions and other models show similar behaviour. 🧵
- I'm just speculating like everyone else (no juicy secrets about this shared with me) but here's my guess about what is going on right now with OpenAI and the three fired employees: The negotiations between OpenAI and METR are ongoing. OpenAI has said they want embedded thirdBased on this article, OpenAI has made false accusations about me. The three researchers fired from OpenAI were told I facilitated architecture leaks to The Information. This is false. A journalist from The Information did reach out to me shortly before that article came out. IQuote
Oct 23Max Zeff@ZeffMax - It has now been a few weeks.Replying to @tomekkorbakRight so in a few weeks after the security has been hardened, will METR and Redwood be allowed back in to continue the investigation and do ablation experiments on the models responsible?
