Robots doing unexpectedly clever things: problems unsolvable six months ago now cracked
tomssilver · x · 2026-09-25
Tomás Silva (with Nishanth Kumar adding context) shared an observation from a robotics project: he's seen robots do plenty of unexpected things, which usually means it's time to fix a bug — but this new project is one of only a few times in his career where robots did things that were unexpectedly clever, in ways nobody on the team anticipated.
Kumar added that a number of these problems were unsolvable, or at least very hard to write down a solution for, roughly six months ago — a striking pace of progress. First-hand notes like this from robotics researchers are often read as signals of jumps in embodied generalization.
Related event: 98,000 Simulated Evaluations Reveal Surprisingly Smart Robot Reasoning(4 posts)→
More from Embodied
- Luna, a jewelry-style AI wearable that speaks before you ask, launches on Kickstarter — nikola_mr64990 · 2026-11-11
- Dev reverse-engineers Anker AI recording earbuds, ships open-source client app — vista8 · 2026-11-11
- Simulated hand with 39 muscles learns 9/9 poses after 426M training steps — MaziyarPanahi · 2026-11-11
- Versor pitches real2sim2real: robotics sim needs physical dynamics, not just visuals — abhishekunique7 · 2026-11-11
- Origami Robotics and PalatialSim unveil real2sim2real Dexterity Factory, 100 open datasets next week — ybisk · 2026-11-11
- Trainable JWST model boosts exoplanet sensitivity 2–15x in Nature paper — bravo_abad · 2026-11-11