Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings | Research - AI at Meta

Restoring communication for people who have lost the ability to speak or move after a brain injury is a major challenge. While intracranial implants now...

RESEARCH NLP Code World Model Preparedness Report This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI Framework as potentially presenting catastrophic risks, and also evaluated the model's misaligned propensities. Our assessment found that CWM does not pose additional frontier risks beyond those present in the current AI ecosystem. We therefore release it as an open-weight model. Daniel Song, Peter Ney, Cristina Menghini,…

saved by

• Jeff Brown

related reading

• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• From Brain Waves to Words: Brain2Qwerty Offers a New Path to Communication Without Surgeryai.meta.com
• Semantic reconstruction of continuous language from non-invasive brain recordings | Nature Neurosciencenature.com
• Noah Shinnnoahshinn.com
• Brain2Qwerty — Decoding typed sentences from non-invasive brain activityfacebookresearch.github.io
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• Test your interpretability techniques by de-censoring Chinese models — LessWronglesswrong.com
• Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
• Publicationseilab.gatech.edu
• 2310.01405.pdfarxiv.org
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org