Robotics researcher: foundation models cut cost but real progress needs performance gains
GlenBerseth · x · 2026-09-16
Robotics researcher Glen Berseth argues that Minsky's lab already had a robot arm using computer vision to see object geometry, plan paths, and assemble parts in the 1960s — today's foundation models are largely solving the same class of problem, just far cheaper and faster to set up. He contends progress should push performance up, not just the cost curve: more object variety, robustness to the wild, multi-robot/human-robot interaction, real-time closed-loop control, and better hardware — "human hands are still impressive." Self-driving cars show why: decades of effort remain hard because they need real-time closed-loop feedback, not just cheaper static perception plus planning.
More from Embodied
- Anthropic previews Model Hardware Standard to let AI agents run lab instruments — ivan_bezdomny · 2026-09-16
- World's first 10,000-unit-scale humanoid robot factory starts production — yogthos · 2026-09-16
- First M5 Ultra Geekbench leak: 52,516 multi-core, ~35% faster than M3 Ultra — jedisct1 · 2026-09-16
- Fei-Fei Li's World Labs is hiring robot learning researchers to scale world models — YunzhuLiYZ · 2026-09-16
- Figure CEO Brett Adcock Shows Off New F.03 Humanoid Robot at Dreamforce — adcock_brett · 2026-09-16
- Berseth: Self-driving shows cost cuts aren't enough — real-time closed-loop control is the hard part — GlenBerseth · 2026-09-16