Scientists Can Read Your Inner Monologue

Scientists have built an AI that can reconstruct what you're thinking — from brain scans alone. In 2023, researchers in Texas decoded continuous language from fMRI recordings while people listened to podcasts. By 2025, Meta and Stanford pushed it even further. Here's what the "semantic decoder" actually does, what it gets hilariously wrong, and the honest limits the headlines always skip. CHAPTERS 0:00 What if scientists read your mind? 0:58 Inside the lab 1:46 How the decoder works 2:55 What it gets right — and wrong 3:57 What the headlines leave out 5:20 The 2025 chapter 6:26 What it means for you 7:43 What IS a thought? 8:02 Subscribe RESEARCH & SOURCES Tang, LeBel, Jain & Huth (2023), "Semantic reconstruction of continuous language from non-invasive brain recordings," Nature Neuroscience. DOI: 10.1038/s41593-023-01304-9 Tang & Huth (2025), cross-subject decoder, Current Biology. DOI: 10.1016/j.cub.2025.01.024 Meta Brain2Qwerty (Lévy et al., preprint 2025; Nature Neuroscience 2026). DOI: 10.1038/s41593-026-02303-2 Kunz, Meschede-Krasa & Willett (2025), inner speech decoding, Cell Horikawa / NTT "Mind Captioning" (2025), Science Advances. DOI: 10.1126/sciadv.adw1464 DISCLAIMER This video is for educational and entertainment purposes only. It is not medical, psychological, or professional advice. The studies discussed are real published research; interpretations are simplified for a general audience. If you're struggling with your mental health, please reach out to a qualified professional. #psychology #mindreading #neuroscience #whyyoufeel #brain mind reading, scientists read minds, inner monologue psychology, brain decoder AI, fMRI mind reading, semantic decoder, neuroscience breakthrough, can AI read your thoughts, psychology of thoughts, why you feel, brain computer interface, thought decoding, Tang Huth decoder