DeepMind researcher: all model inputs are arbitrary binary codes, so images aren't magic for understanding

AndrewLampinen · x · 2026-09-28

In an X exchange with Stanford linguist Chris Potts, DeepMind researcher Andrew Lampinen argues that all signals these systems process are arbitrary binary codes—we merely interpret chunks as different modalities. Since much of what an image or sensor reading conveys could be said in a chat, he questions the assumption that non-language inputs carry a magical "meaning-ness" essential to understanding, pushing back on the popular claim that multimodal grounding is required for genuine comprehension.

Related event: DeepMind Researchers Push Back on Claim That Only Images Bring Real Understanding(2 posts)→

Original post →

More from Research

Research channel →