Habryka clarifies: denies MIRI takeover, admits CEV brain-in-box plan
ohabryka · x · 2026-08-15
Habryka responds to jdpressman, clarifying his stance: he denies that MIRI tried to take over the world or allowed fans to think so, but admits he was too dismissive of the claim that MIRI planned to build a 'brain in a box' implementing human CEV. He argues this is not a repudiation of the brain-in-box idea but a refutation of the 'MIRI takeover' narrative.
More from AGI Musings
- AI ownership may create abundance humans lack the income to access — PierceLilholt · 2026-10-16
- The Gap Between Very Good and Great: 1 in 100K Fills a Stadium, 1 in 100M Fills a Room — dbasch · 2026-10-16
- ICLR reviewer says 4/5 papers in review pile read like AI slop — berkustun · 2026-10-16
- Turing laureate David Patterson: 99% of science discoveries will be made by AI by end of next year — davidpattersonx · 2026-10-16
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Kroger cuts 3,000 corporate jobs (37%) for AI; humanoid robots next in the 2030s — csuwildcat · 2026-10-16