AIR-O decodes visual attention from brain scans in real time, generating images noninvasively
jonxuxu · x · 2026-11-18
Alljoined unveils AIR-O, a model that decodes what a person is attending to directly from noninvasive brain scans, generating an image from scratch in real time that depicts where their attention is focused.
Author jonxuxu recalls that when the first fMRI-to-image models appeared in 2022, his questions were "is this real?" and "how far can we take this?"—three years of work later, the team is sharing its results.
He argues BCI will play a role in helping exponentially more powerful AI align with humanity's best interests.
More from Research
- Goodfire's Neuron Communities: a handful of neurons in LLMs can handle arithmetic and formatting — fatihdin4en · 2026-11-18
- JAMA study finds AI-generated discharge summaries match clinician-authored ones on harm potential — EricTopol · 2026-11-18
- Hiding Random Data Points Is a Weak Test of Reaction Mechanisms, Chemists Warn — bravo_abad · 2026-11-18
- LoRA dial can precisely fake low benchmark scores: up to 97% of faked errors land on one letter — rohanpaul_ai · 2026-11-18
- Study finds latest Claude models were trained on protein sequences at scale — LeoTZ03 · 2026-11-18
- Reviewer fatigue in the coding-agent era: "everything is possible, nothing is interesting" — rishabh16_ · 2026-11-18