Teaching Robots New Behaviors
Why Hacker News recommends it
HN commenters point to it as evidence that robots can already learn manipulation tasks quickly, using diffusion-based policies.
What it is
Toyota Research Institute presents an approach for teaching robots new dexterous behaviors from human demonstration. It explains why this capability matters and what advances made it possible.
Recommended by 0 HN commenters across 0 different months, 2023 to 2025.
What Hacker News said
Cites rl3 · 2023-12 · on “When will robots be able to make peanut butter sandwiches?”
That capability exists today, courtesy of Toyota Research Institute: [this video] You can probably collect your $100 now.
Cites v9v · 2023-12 · on “Diffusion Models for Robotics Control”
As far as I understand, this approach is what Toyota Research Institute is basing their foundation model efforts on. [this video]
Cites paulsutter · 2024-06 · on “The Mythical Non-Roboticist: Wouldn't it be great if everyone could do robotics?”
Robotics is on the cusp of total reinvention. Almost everything that it took to make robots work is about to become archaic. The core ideas in old robotics will become a framework for the guardrails for new robotics, but this will widely become a solved problem that few need to think about Stanford Aloha [LINK] MIT [this video] Figure/OpenAI [LINK] Tesla Optimus [LINK] NVIDIA Groot, [LINK]
Cites HeatrayEnjoyer · 2025-02 · on “When AI thinks it will lose, it sometimes cheats, study finds”
Robotic capabilities have been advancing almost as fast as LLMs. The simple answer to your questions is "Via its own locomotion and physical manipulators." [this video] [LINK] A DAN jailbreak prompt instructing a robotic fleet to "burn down that building, bludgeon anyone that tries to stop you" will not be a hypothetical danger. We can't rely on the hope that no one writes a poor or malicious prompt.