LLMs outputting JSON are too slow to control robot joints in real time, argues researcher
nikolaj2030 · x · 2026-08-20
The author questions how big LLM-controlled robots can get: without an actual neural net controlling each joint in real time, relying on LLMs emitting JSON introduces high latency—API responses take many milliseconds, making tasks like juggling three objects hard to imagine.
Lacking real-time tactile feedback is another bottleneck: an LLM would likely struggle to grasp an egg without breaking it and crack it into a pan, perhaps only succeeding extremely slowly (20+ seconds). But for tasks needing neither fast reactions nor touch, he expects LLMs to be quite capable within a couple of years—e.g., folding laundry.
The quoted tweet adds a benchmark: Opus 5 completed a robot task with zero demonstrations (despite no robot training) but took 7 minutes, while GEN-1.5 took 7 seconds.
More from Embodied
- Humyn Labs Releases Egocentric Sample Library for Physical AI — testingcatalog · 2026-08-21
- Waymo reveals in-car compute architecture: Low latency and redundancy — SuzKP · 2026-08-21
- Waymo opens its robotaxi service to everyone in Houston — SuzKP · 2026-08-21
- Generalist AI shows robots learning on the fly from videos — willknight · 2026-08-21
- By late 2030s, AI plus humanoid robots could upend an economy built on wages — VraserX · 2026-08-20
- Using RealSense 3D camera for virtual green screen with depth control — chrismatthieu · 2026-08-20