Thinking in Silico: Goodfire CTO Dan Balsam on Concept Manifolds & a $1000/Month ML Research Agent

About this episode

Goodfire co-founder and CTO Dan Balsam returns to discuss where interpretability research now stands and to introduce Silico, the $1,000-per-month research platform Goodfire built for itself. He and Nathan explore Predictive Data Debugging, including the idea that fine-tuning and RL often amplify behaviors already latent in pre-training, and that interpretability can identify the data and features driving unwanted updates. The conversation centers on concept manifolds: Dan argues that models do not store concepts as simple one-hot features, but as sparse mixtures of meaningful subspaces whose geometry determines what kinds of steering and control work. The stakes are practical as well as conceptual, from debugging training data and RL to understanding why steering can fail off-manifold and why modern interpretability may be moving beyond its reputation as a toy-model science. Silico: https://www.goodfire.com/silico Predictive data debugging: https://www.goodfire.com/research/predictive-data-debugging# Neural Geometry: https://www.goodfire.com/research/the-world-inside-neural-networks# For full show notes, links, and references, read the episode page:https://www.cognitiverevol