MIRI's Early FAI Ambitions Spark Heated AI Safety Debate

jd_pressman · x · 2026-08-16

In an AI safety community debate, participants argue over whether MIRI was genuinely committed to building Friendly AI (FAI) in 2011-2013. JD Pressman claims MIRI believed it could achieve AGI first through mathematical purity, while others counter that MIRI never worked on AGI in a basement and that evidence is lacking. The discussion also touches on whether MIRI aimed to 'take over the world' and the ethics of CEV.

Related event: Did MIRI Ever Aim to 'Take Over the World'? AI Safety Community Feuds Over FAI History and CEV(25 posts)→

Original post →

More from AGI Musings

AGI Musings channel →