Sampura Research - Talk+Social

Sampura Research: Hill-climbing Alignment using Humans Sampura Research is a London-based nonprofit, founded by Google DeepMind alumni, building Human-AI Complementarity for AI alignment. As AI systems grow more capable, the judges we use to train, evaluate and monitor them increasingly fall short. Most of the field responds by replacing humans with LLM judges; we think humans and AIs have complementary strengths, and that human oversight is an uncorrelated layer of defence that AI-only judges can't provide. In this talk we'll share how we're building better judges: a leaderboard of 50+ alignment-relevant datasets, and methods that route, decompose and assist across humans and AIs to hill-climb it. Backed by an $11M grant from Coefficient Giving, we're a small in-person team hiring founding technical staff, looking to solve alignment instead of just pausing AI. Come along and say hello! Schedule (co-hosted by Carnegie AI Safety Initiative)13:00 – Talk (30 min)13:30 – Q&A (20 min)13:50 – Informal chat (10++ min)Location: Room GHC 6115, Gates Center for Computer Science, Carnegie Mellon UniversityOr, join virtually: Meet Link Want to meet separately?Please add your info in this Google Sheet, or email [email protected]! Apply: Founding Member of Technical Staff applicationJoin our mailing list: Mailing ListWebsite: sampura.org