Four AI models in a claimed real-time, zero-shot robot-control comparison
A user describes a video comparing GPT-6 Astra, Opus 5.5, Grok 4.7 and MolmoAct2 as unsped and not cherry-picked. They say LLM robot control is progressing but has a way to go.
TLDR
A user shares a video comparing GPT-6 Astra, Opus 5.5, Grok 4.7 and MolmoAct2, describing the comparison as real-time, unsped, zero-shot and not cherry-picked. They say LLM robot control is progressing but remains short of the mark, and cite Moravec’s paradox to argue that low-level robotics control still matters.
Combined views
23.2K
2 Sources, first seen 11h ago
