New approaches to interpretability from Google DeepMind
Details about Gemini 2.5 playing Pokémon
Hello, fellow human! I’d love to share some of our upcoming virtual talks that might be interesting to you.
Next Thursday, September 25, we are hosting a discussion with Been Kim, a Senior Staff Research Scientist at Google DeepMind. Been has dedicated her career to understanding how machines work and bridging the gap between humans and machines.
We will discuss novel approaches to interpretability, the current challenges, and how the field might evolve with more powerful AI systems.
The talk is virtual, I hope to see you there!
Here is the registration link.
We also recently spoke with Kiran Vodrahalli from Google DeepMind about the details of training Gemini 2.5 to play Pokémon, and how long-context and self-improvement techniques helped the model achieve strong performance in the game.
Really excited for the Been Kim talk! Interpretability is becoming more critical as models scale, and I'm particularly interested in how the field adapts when dealing with emergent behaviors we didn't explicitly program. The Pokémon work with Gemini 2.5 is fascinating too - long-context self-improvemet opens up interesting questions about how models can bootstrap their own performance in complex sequential decision-making tasks. Looking forward to both discussions!