Can We Hill-climb Alignment using Humans? | Sampura Research [Talk+Social]

Sampura Research: Hill-climbing Alignment using Humans

As AI systems grow more capable, the judges we use to train 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.

Schedule
7pm - Doors open + mingling
7:30pm - Talk (30 min)
8pm - Q&A

Sampura Research is a London-based nonprofit, founded by Google DeepMind alumni, building Human-AI Complementarity for AI alignment.

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 pausing AI. Come along and say hello!

Apply: Founding Member of Technical Staff application
Website: https://sampura.org/