How does a robotics agent recover task state after a Wi-Fi drop? Sentdex demo prompts question
petrusenko_max · x · 2026-11-22
Following sentdex's robotics harness demo (DSV41F-1017), a developer asked a key engineering question: when the loop picks itself back up after Wi-Fi drops, how does it know the grasp in progress hadn't already finished? In the demo, an LLM was told to find any "children's toy", grab it and deposit it into a black bin — solved on the first attempt with a never-before-seen toy, with added on-screen debugging showing what the robot is thinking.
Related event: Sentdex Shows LLM-Controlled Robot Autonomous Toy Pickup(3 posts)→
More from coding & agent
- LangChain CEO: enterprises need a 'knowledge factory', not better models — hwchase17 · 2026-11-22
- Harrison Chase: buying Copilot won't transform teams without a knowledge factory — hwchase17 · 2026-11-22
- Aiden Bai doubles down: "** agents!!!" — aidenybai · 2026-11-22
- Cognition CEO Aiden Bai says he never reads the code, just watches agent test videos — aidenybai · 2026-11-22
- Long-running agents fail by re-litigating old decisions, not by crashing — ClickOk5811 · 2026-11-22
- NBER study of 500k+ GitHub devs: coding agents boosted commits ~240% but releases only ~30% — Antique_Atmosphere97 · 2026-11-22