A Worm With 302 Neurons Inspired Their Architecture — Ramin Hasani, Liquid AI
Source
youtube.com
Author
Latent Space
Date
Why it matters
Explains how architectures can be searched automatically for target hardware (CPU, GPU, NPU), which matters for engineers weighing on-device or low-latency model deployment.
Key takeaways · AI-distilled
Hasani notes C. elegans handles complex motor control with 302 neurons that behave like artificial neurons rather than spiking, which led Liquid toward continuous-time models instead of spiking networks.
On scaling recurrent models, Hasani warns there is no free lunch: linearizing complicated dynamics to make them tractable loses expressivity.
Liquid partners with enterprises including Shopify and Mercedes-Benz on on-device or private deployments, and maintains an open library, Leap, for fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition → and deploying models in formats like GGUF.
Hasani estimates about 90% of the market is inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition →tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → today and expects the next wave of companies to capitalize on customization tokens.
Terms in this piece · Glossary
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
video🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)
video🔬 Google's AI Scientist Started as an Attempt to Automate Kaggle — John Platt, Google Fellow
videoOrbs: Shifting Coding to Cloud — Quinn Slack, Amp Code
videoRecursive Self-Improvement: from Auto Research to Superintelligence — Richard Socher, Recursive
