2 results
MIT professor Phillip Isola discusses what makes learned representations useful and why independently trained models can develop similar internal structure. He explores the platonic representation hypothesis, local clustering versus global geometry, and the neural thickets account of why pretrained networks can adapt readily to downstream tasks. Other topics include language models as world models, recurrent architectures, biological comparisons, and studying autonomous language-model agents as artificial life. Hosted by Ravid Shwartz Ziv and Allen Roush; watch the full research conversation on YouTube.
Hosted by Ravid Shwartz Ziv, Allen Roush
Published Jul 2, 2026 · 1 h 11 min
Paul Middlebrooks and Johannes Jaeger discuss agency in living systems, relevance realization, consciousness, energy efficiency and why biological organisms differ from artificial agents.
Published Jul 1, 2026 · 1 h 37 min