Me, trying to sleep: My brain: The Caesar cipher can be broken down with a brute force approach Me: ffs, I gotta tweet this

Bitcoin is an exit from the Fed. DeFi is an exit from Wall Street. Social media is an exit from mass media. Homeschooling is an exit from industrial education. Remote work is an exit from 9-5. Creator economy is an exit from employment. Individuals are leaving institutions.

Some book titles are so beautiful, they read like one-line poetry even if you don't know what the book is about • On Earth We're Briefly Gorgeous • The Unbearable Lightness of Being • To Kill a Mockingbird

TIL there are olfactory receptors in our tongue. Means we can smell with our tongue too. Wild.

You judge yourself based on your intention, and everyone else based on their behavior.

GPU Programming: Think 256 times, code once.

Six threads better than a college degree:

You don't wanna make people believe what you're saying; you wanna make people believe that you believe in what you're saying.

In the last 20 years, software ate the world. In the next 20 years, AI will eat software.

How to Win (without talent or luck) by Sahil Bloom A visualised thread 🧵👇

you have access to your optimal policy at all times. you just choose not to follow it. you can literally access it by asking “what should i be doing rn?”

wohooo 🎉firsts of many special firsts at GT 😊 huuge thanks to awesome dr. Dyer and rockstar Mehdi for giving me the opportunity to be a part of this!

Oh Yea!

Is a universal brain decoder possible? Can we train a decoding system that easily transfers to new individuals/tasks? Check out our #NeurIPS2023 paper where we show that it’s possible to transfer from a large pretrained model to achieve SOTA 🧠! Link: poyo-brain.github.io 🧵

Super excited to share new work to appear at #NeurIPS2023 led by the incredible Mehdi Azabou! In collaboration with an amazing team: Vinam Arora, 🤖, Ximeng Mao, Santosh Nachimuthu, Michael Mendelson, Blake Richards, Matt Perich, Guillaume Lajoie Patrick Mineault Machine Learning at Georgia Tech 🧠🤖

This was a Ginormous effort - so proud of our team (Eva Dyer 's nerds), and super lucky to be a small part of this 🥳 rockstar Mehdi Azabou just getting started 🔥🔥

My internal negotiator for choosing between short term and long term rewards needs a serious upgrade

How can we extract insights from behavior modulated by multiple complex factors? 🐭🪰🤖🏃 Check out our #NeurIPS2023 Spotlight Paper where we present a SSL method for learning multiscale representations of behavior! Machine Learning at Georgia Tech Google DeepMind Link: multiscale-behavior.github.io 🧵

we just shipped our most capable video-to-video lipsyncing model yet introducing lipsync-1.8.0 🪄 edit what anyone says in any video, no training required available now via API + v2 playground. check it out 👇