lab

Center for Responsible, Decentralized Intelligence

Research center at UC Berkeley working on responsible and decentralized AI, including the trustworthiness of model and agent evaluation. It publishes its findings on the rdi.berkeley.edu blog.

Known aliases

Berkeley RDI
RDI
RDI Berkeley

Relationships

No evidence-backed relationships are recorded.

Current clusters

science1 publisher

A Berkeley scanning agent scores 100% on five AI agent benchmarks without solving a task

Berkeley's RDI center attacked the step where each benchmark computes its score, and without solving a task its own scorecard reports 100% on five of the eight, about 98% on GAIA and 73% on OSWorld.

Publishers:rdi.berkeley.edu

Reality

Evidence45
Adoption35
Hype gap+20
Incentives55
Confidence50