Oxford thesis proposes 'Attribution-Based Control' to tackle AI privacy and alignment risks

iamtrask · x · 2026-09-14

Andrew Trask's Oxford DPhil pre-print 'Attribution-Based Control in AI Systems' argues that AI risks spanning privacy, value alignment, copyright, concentration of power, and hallucinations reduce to a single problem: the lack of attribution-based control (ABC), rooted in overuse of addition, copying, and branching in gradient descent.

Key points:

Original post →

More from Safety

Safety channel →