Closed-loop monkey experiments reveal hidden gaps in AI model-brain alignment across 25 neural sites
CSProfKGD · x · 2026-10-10
Jacob Prince's team ran large-scale closed-loop monkey experiments at 25 neural sites: while leading AI models appeared equally good at predicting brain activity, asking them to synthesize images that precisely control neural firing exposed striking hidden differences in model-brain alignment. The work produced 27k+ feature visualizations spanning mid-to-high-level visual areas (inferotemporal cortex, superior temporal sulcus), showcasing a compelling application of interpretability research.
More from Research
- Retrieval-centric deep learning: replacing weight matrices with vector databases — RobertTLange · 2026-10-10
- SJTU's UVTA teaches robot dexterous manipulation from 1,000 human tactile demos per task — siyuanhuang95 · 2026-10-10
- 20-minute explainer breaks down how Tesla trains FSD: 8 cameras, 36fps, 2B signals to 2 outputs — PTrubey · 2026-10-10
- 21 researchers release white paper on Visual General Intelligence as a path to AGI — HirokatuKataoka · 2026-10-10
- Epoch AI: Over half of arXiv math papers in 3 subfields now acknowledge AI use — burny_tech · 2026-10-10
- Researcher faults standard Transformer diagrams for hiding self-attention as a black box — PlisSergey · 2026-10-10