Scott Aaronson to teach AI Alignment course at UT Austin, Yudkowsky first reading
teortaxesTex · x · 2026-10-08
In 2026, Scott Aaronson is teaching a course at UT Austin formally titled 'AI Alignment Theory', with Yudkowsky's AGI Ruin: A List of Lethalities as the first assigned reading. Commenters note this marks Yudkowsky's ideas entering mainstream academia.
More from AGI Musings
- OpenAI math problem #109 tightened ~570-million-fold via nonadjacent axis swaps — aran_nayebi · 2026-10-08
- 'What EA/AI safety folks miss is…': the tell that you're retreading old literature — JacquesThibs · 2026-10-08
- If AI automates math, the frontier shifts from solving problems to asking deeper ones — xwang_lk · 2026-10-08
- Self-Copying AI Breaks One-Person-One-Vote: Social Theory Needs a Rework — jacyanthis · 2026-10-08
- AI Identity as Animism: Every Chunk of Information Can Talk — jacyanthis · 2026-10-08
- In a Society of Digital Minds, 'Individual' Will Be Fluid and Nested — jacyanthis · 2026-10-08