Scott Aaronson, a professor at the University of Texas at Austin, is teaching a new course on AI Alignment Theory. Due to the rapid advancements in AI, the course structure resembles a humanities seminar, with students presenting and discussing various readings on AI alignment. Aaronson has made the course's reading list and student-generated rapporteur reports publicly available, intending to update them throughout the semester as a central repository for the course's materials. AI
IMPACT Provides access to curated readings and student analyses on AI alignment, aiding researchers and students in understanding complex safety concepts.
RANK_REASON The item details course materials and readings related to AI safety and alignment theory, which falls under academic research. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — mastodon.social →
- AGI Ruin: A List of Lethalities
- AI Alignment Theory
- Amodei
- Bertrand Russell
- Chan
- Christiano
- Concrete Problems in AI Safety
- Dwayne Johnson
- Eliezer Yudkowsky
- Mane
- Mindermann
- Olah
- Open Letter on Artificial Intelligence
- Schulman
- Scott Aaronson
- Steinhardt
- The Alignment Problem from a Deep Learning Perspective
- University of Texas at Austin
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
