Attribution-Based Control for AI ⬩ OpenMined
Discover how attribution-based control solves AI's biggest problems: hallucinations, privacy violations, and loss of data control. Free open-source solution from OpenMined.
Attribution-Based Control for AI ⬩ OpenMined Skip to main content Skip to footer Introduction to Attribution-Based Control (ABC) A New Paradigm for Safe, Trustworthy, Responsible AI Many of AI’s risks in areas like AI evaluations, privacy, value alignment, copyright, concentration of power, loss of control, and hallucinations can be reduced to the lack of attribution-based control in AI systems, which itself can be reduced to the overuse of addition and copying within AI algorithms. OpenMined’s primary technical goal is to synthesize a handful of recently proposed techniques in dee
Explore this link on the map →saved by
related reading
- AI 2027ai-2027.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Unlocking a Million Times More Data for AI | IFPifp.org
- 2028: Two scenarios for global AI leadership \ Anthropicanthropic.com
- Research Areas in AI Control (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- The Case Against AI Control Research — LessWronglesswrong.com
- Introduction to AI Control - by Sarah - BlueDot Impactbluedot.org
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Reading Listblog.redwoodresearch.org
- There Is No A.I. | The New Yorkernewyorker.com
- AI 2027ai-2027.com
- Request for Proposals — Checks and Balances in an Automated Societychecks-and-balances.ai