Ai2 @ai2.bsky.social · 18/03/2026Grounding lets vision-language models do more than describe—they can point to where a robot should grasp, which button to click, or which object to track across video frames. Today we're releasing MolmoPoint, a better way for models to point. 🧵 2206
Max Slinger @promptslinger.bsky.social · 18/03/2026Six weeks wiring GPT-4V into UI automation last year taught me one thing. Spatial grounding breaks the moment two similar buttons share a screen. Curious what Mo's accuracy looks like on cluttered real world layouts 110
Ai2 @ai2.bsky.social · 18/03/2026Most VLMs point by generating text coordinates—essentially dictating numbers. It works, but it wastes tokens, breaks at high resolutions, and forces models to learn an abstract numbering system that has nothing to do with how they actually see. 110
