Research
Developing reliable AI tools for healthcare
Technical blog
An early warning system for novel AI risks
Technical blog
AI for the board game Diplomacy
Technical blog
Benchmarking the next generation of never-ending learners
Technical blog
How undesired goals can arise with correct rewards
Technical blog
In conversation with AI: building better language models
Technical blog
From motor control to embodied intelligence
Technical blog
Discovering when an agent is present in a system
Technical blog
Perceiver AR: general-purpose, long-context autoregressive generation
Technical blog
Intuitive physics learning in a deep-learning model inspired by developmental psychology
Technical blog
Human-centred mechanism design with Democratic AI
Technical blog
BYOL-Explore: Exploration with Bootstrapped Prediction
Technical blog
Unlocking High-Accuracy Differentially Private Image Classification through Scale
Technical blog
Evaluating Multimodal Interactive Agents
Technical blog
Dynamic language understanding: adaptation to new knowledge in parametric and semi-parametric models
Technical blog
Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning
Technical blog
A Generalist Agent
Technical blog
Active offline policy selection
Technical blog
An empirical analysis of compute-optimal large language model training
Technical blog
GopherCite: Teaching language models to support answers with verified quotes
Technical blog
Learning Robust Real-Time Cultural Transmission without Human Data
Technical blog
Probing Image-Language Transformers for Verb Understanding
Technical blog
Red Teaming Language Models with Language Models
Technical blog
Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents
Technical blog
Improving language models by retrieving from trillions of tokens