🎉 Our Meta-RL survey is now published in Foundations and Trends in Machine Learning! A deep dive into how agents can learn to learn 🤖🧠 Huge kudos to Jacob Beck & Risto Vuorio for leading the charge, and to co-authors Evan Liu, Zheng Xiong, Chelsea Finn & Shimon Whiteson!

After 25 yrs of school, 5 yrs of research, and many dilapidated British pubs, my PhD on meta-RL is DONE! New chapter: I’ve joined Oracle as a Research Scientist in AI! Come say hi if you’re in Boston! Thesis: ora.ox.ac.uk/objects/uuid:2… Job: labs.oracle.com/pls/apex/f?p=9…

Heading to @rl_conference (RLC) today! Come say hi if you’re around—happy to chat about meta-RL, coding agents, and my work at @RLBrew_RLC tomorrow on VLM feedback for RL 🍁

🥳 It’s an honour to have been awarded the Outstanding Paper for Scientific Understanding in RL at RLC for our work, ‘How Should We Meta-Learn RL Algorithms?’ Thank you to the organisers RL_Conference for putting on a great conference, and congratulations to the other winners!

Hey I recognize those people! Alex Goldie @ RLC 25

Thoughts on this? AI is trained to follow prompts, making it highly amenable to alignment. The only time we train it not to obey is for safety constraints, such as refusing to build a bioweapon. The real danger isn’t disobedient machines. It’s humans, misaligned with each other.

Thoughts on this? The possibility of exponential AI self-improvement is shaky. The real bottleneck isn’t code; it’s compute & data. In these areas, AIs training AIs are just as limited by the world as humans training AIs. For both, we’ve nearly exhausted the internet’s data.

E71: Jake Beck, Alex Goldie, & Cornelius Braun on Sutton's OaK, Metalearning, LLMs, Squirrels @ RL_Conference 2025 A few thoughts with Jacob Beck, Alex Goldie @ RLC 25 and Cornelius Braun after Richard Sutton's fascinating lecture on his OaK architecture at University of Alberta