Latent Space interview: Liquid AI's Ramin Hasani on architecture inspired by a 302-neuron worm
Latent Space · youtube · 2026-09-19
Latent Space interviews Liquid AI co-founder Ramin Hasani, whose architecture research traces back to the C. elegans worm's 302-neuron nervous system. The conversation covers how Liquid Neural Networks' time-varying weights evolved into Liquid AI's efficient foundation models — a useful deep dive for anyone tracking non-Transformer architecture routes and bio-inspired design turning into a business.
More from Companies & People
- AssemblyAI Hosts SF Tech Week Workshop Building Voice Agents Into Vintage Toys — AssemblyAI · 2026-09-19
- Pedro Domingos: OpenAI and Anthropic's real moat is their massive secured compute — pmddomingos · 2026-09-19
- PyTorch Conference to feature Muon optimizer, TorchJD and LLM serving tools from Meta, Google, NVIDIA — PyTorch · 2026-09-19
- Dev asks why Scale AI's gov ties and eval consulting record get so little scrutiny — willcb · 2026-09-19
- Databricks CEO Ali Ghodsi Praised as Silicon Valley's Best: Reviews Every Feature, Replies in 20 Minutes — Yuchenj_UW · 2026-09-19
- Zuckerberg Says No AI Slowdown Needed: Market Forces Will Keep Models Safe — fortune · 2026-09-19