Miscellaneous

Talks & Media

The Emergence of Intelligence: From Bitter Lessons to Universal Minds

Talk at Oxford University on the emergence of capabilities and behaviour in AI systems and their links to classical emergence.

June 2025

Structured World Representations in Maze-Solving Transformers

Podcast discussion about our work on understanding how transformers learn to represent and solve maze navigation tasks.

June 2024

Sparse Relational Reasoning with Object-Centric Representations

Conference talk from ICML 2022 DyNN Workshop on the benefits of sparsity and structured representations for neural relational reasoning.

July 2022

Projects

AI Safety Papers Site

Curated and automated collection of AI Safety papers and resources

ai-safetyresourceweb
ML Experiment Sweeper

A tool for running machine learning experiments across different compute environments (SSH, Local, etc.)

toolpythonml-ops
haiku_probe

A set of lightweight tools for mechanistic interpretability, probing ANNs built in Haiku. Implements probing/interventio...

mechanistic-interpretabilitypythonhaikuneural-networks
AIHack2022: MicroDroP

1st Place Winner at AIHack2022 - Microfluidic Droplet Coalescence Prediction using Hamiltonian Neural Networks.

deep-learningphysics-informed-mlcomputer-visionhamiltonian-networks
Neuropixel Grid Cell Analysis

Analysis of salient neurons representing grid cell activity using neuropixel data from mice, developed for the Neuroscie...

neurosciencedata-analysispythongrid-cells