I Saw the Future of AI in a Robot That Can Learn on the Spot
ArtificialOther · x · 2026-08-22
WIRED senior writer Will Knight visited Generalist AI, documenting how robotic arms mastered new tasks after watching short instructional videos without specific training.
Key Observations
- In-Context Learning: Robots perform tasks like stacking cups by ingesting demo videos.
- Tool Use & Improvisation: When a brush was removed, a robot improvised by flicking a block into a bowl with a dustpan; another robot unzipped different purse styles and switched hands to grab banknotes better.
- Technical Analogy: Cofounder Pete Florence compares this to GPT-3's prompting ability, where the model attempts new tasks without fine-tuning.
Related event: WIRED visits Generalist AI: robots learn new tasks on the fly(4 posts)→
More from Embodied
- EmbodiedEvo tops RoboDojo as agents inherit reusable skills and lessons — Aiden_Tech_Ai · 2026-10-16
- Sunday Robotics is hiring a Senior Infra PM to scale consumer robot deployments — saranormous · 2026-10-16
- Bond's Submarine Lotus Esprit Spotted at Event, Fueling Steering-Wheel-Free Robotaxi Speculation — PTrubey · 2026-10-16
- Maker wires Grok and Claude into ROS2 robot with RealSense stereo cameras — chrismatthieu · 2026-10-16
- NEURA Robotics launches Neuron AI, a unified Perception-Language-Action model for robots — Distinct-Question-16 · 2026-10-16
- Dev demos open wearable AI passport running multilingual flashcards on tiny memory — ezshine · 2026-10-16