Last week I asked what the most promising theory of consciousness was. Here are the results. #1 - Michael Graziano’s Attention Schema Theory (AST) 1/n 🧵

In 2016, at an AI conference in NYC, I explained artificial consciousness, world models, predictive coding, and science as data compression in less than 10 minutes. I happened to be in town, walked in without being announced, and ended up on their panel. It was great fun.

This timelapse sequence shows how critical naval and aviation parts like a 900 mm diameter three-blade propeller or an aerospace propeller tank are 3D printed in stainless steel [📹 Meltio]

Say hello to GPT-4o, our new flagship model which can reason across audio, vision, and text in real time: openai.com/index/hello-gp… Text and image input rolling out today in API and ChatGPT with voice and video in the coming weeks.

Excited to announce my translation work is out! 🎉 I translated Mark Solms' "#TheHiddenSpring" into Korean. He dives into the hard problem of consciousness, using #FreeEnergyPrinciple. Who knew the mind's mysteries could be so captivating? 🧠🤖 #Neuroscience #Consciousness

🚀 Just wrapped up my Active Inference & Free Energy Principle study group! 🎉 Over the past months, we explored these complex topics through 22 recorded sessions: youtube.com/playlist?list=… #ActiveInference #FreeEnergyPrinciple #KACS #neuroscience #AI

この論文を今日知ったのだが、こういうのがNISTから出ているというのが興味深い。 Consciousness is learning: predictive processing systems that learn by binding may perceive themselves as conscious arxiv.org/abs/2301.07016

Available now! #REACH2024: The Brain Issue explores the bold questions CIFAR researchers are pursuing to unlock the mysteries of our most intricate organ — from understanding the roots of consciousness to uncovering the gut-brain axis. Read it here: cifar.ca/publications-r…

Sugihara's

The universe creates complexity out of simplicity, but despite many attempts at understanding how, scientists still don't understand it. One thing we do know is that it relies on emergence. A group of scientists has now made big progress on explaining it youtube.com/watch?v=Tw9sr0…

Daily Training of Robots Driven by RL Segments of daily training for robots driven by reinforcement learning. Multiple tests done in advance for friendly service humans.😊 The training includes some extreme tests, please do not imitate. #AI #Unitree #AGI #EmbodiedIntelligence

What's the difference between simulating and replicating consciousness in artificial systems? Here's my take on artificial consciousness: link.springer.com/article/10.100…

I’m so happy that this work is finally on arXiv! “Evolving reservoir computers reveals bidirectional coupling between predictive power and emergent dynamics” arxiv.org/abs/2406.19201 A huge thank you to the great team of co-authors Andrea Luppi, Anil Seth and Pedro Mediano!

A landscape of consciousness: Toward a taxonomy of explanations and implications sciencedirect.com/science/articl… - A comprehensive overview of theories by Robert Kuhn, Closer To Truth - it's no wonder we can't agree!

오늘 정말 존경하는 #아닐세스 교수님과 대화를 나누는 특별한 시간을 가졌습니다. 많은 영감을 받았습니다! Thank you, Anil Seth, for the enlightening conversation. It was a truly valuable experience that left me deeply inspired! #assc27 #Consciousness #predictivecoding #내가된다는것

Amazing discussion today:) Thank you for Biyu Jade He and speakers

Friday morning poster session:) Cool works from Chatrin Suksasilp !! Lovely approach from #activeinference to #metacognition and #interoception 🙌🏻 #ASSC27 #consciousness

"In 1956, Massachusetts Institute of Technology (MIT) Prof Claude Shannon writes a one-page article trying to curb the information theory #hype." (terse text above by Alex Vasilescu; h/t Palle Jorgensen & Carina Curto)

Data often exhibit non-Euclidean structure: From the curvature of space-time🌐, to topologically complex interactions between neurons🍩, to algebraic transformations describing symmetries in physical systems💎. How can ML/AI best process this data? Check out our new review!