Can a general multimodal LLM do the high-level robot reasoning?
Loading video
Loading videoSentdex tests whether ordinary open multimodal LLMs, not trained for robotics, can handle the high-level intent and reasoning layer that VLA and world-action-style robot stacks are chasing.
Category: research
Author: @Sentdex
Date: 2026-09-03T00:00:00
Duration: 43.316s
