Sentdex runs a <$1K quadruped on GLM's vision model, testing generic multimodal LLMs as robotics brains
Sentdex · x · 2026-09-04
Sentdex demonstrates an experiment: using a general-purpose multimodal LLM with vision understanding (GLM 5.3 Flash) to handle high-level robotics intelligence, instead of purpose-built VLAs or world models. He argues recent open-source multimodal LLMs have become fast and smart enough to make this viable.
He also recommends a <$1K quadruped from Luwu Dynamics, which he has been testing for 5 years and calls the best one yet; a full video is coming.
Related event: Sentdex drives a quadruped robot with a general multimodal LLM(3 posts)→
More from Embodied
- Perceptron's Isaac 0.5 robot folds t-shirts, ships open weights for cross-embodiment repro — iamrobotbear · 2026-09-04
- Lab lessons from Anthropic MHS: keep fast control out of the model — Empty-Abalone-2952 · 2026-09-04
- Build or OEM? Nvidia Fabless Lesson for Humanoid Robot Makers — chris_j_paxton · 2026-09-04
- Sentdex shows general multimodal LLMs can drive robots with zero training — Sentdex · 2026-09-04
- "Atlas <> Palantir" teaser surfaces, pointing to a September 10, 2026 reveal — eliano · 2026-09-04
- Ultra's hybrid robotic-arm plus semi-humanoid strategy targets rapid 3PL field deployment — chris_j_paxton · 2026-09-04