Proposed test: can a warehouse robot still stop in time while its LLM is mid-reasoning?

krishnan · x · 2026-11-18

krishnan proposes a test (not a reported SiMa deployment): a warehouse robot hits an unexpected obstruction mid-reasoning-request. Under combined load, do perception and the stop response still meet deadlines? Speculative decoding speeds up tokens but doesn't prove perception stays fresh during long reasoning — the first question a buyer should ask.

Related event: krishnan questions SiMa.ai Palette 3.0's single-chip robot AI claims(8 posts)→

Original post →

More from Embodied

Embodied channel →