Theoretical Computer Science for AI Alignment group (Scott Aaronson, UT Austin)

Scott Aaronson’s Theoretical Computer Science for AI Alignment group at UT Austin applies his expertise in computational complexity and quantum computing to questions motivated by AI alignment and safety. Building on his two-year leave at OpenAI to work on the theoretical foundations of AI safety, the group supports students and postdocs to investigate how complexity-theoretic and related tools can clarify the capabilities and limitations of advanced AI systems.

Endorsements support University of Texas at Austin.

No endorsements yet.

Discussion

Start Date

-

End Date

-

Expected Duration

-

Funding Raised to Date

-