🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

In collaboration with Google, we're releasing Activation Atlases: a new technique for visualizing what interactions between neurons can represent. 💻Blog: blog.openai.com/introducing-ac… 📝Paper: distill.pub/2019/activatio… 🔤Code: github.com/tensorflow/luc… 🗺️Demo: distill.pub/2019/activatio…

Are you a deep learning researcher? Wondering if all this TensorFlow 2.0 stuff you heard about is relevant to you? This thread is a crash course on everything you need to know to use TensorFlow 2.0 + Keras for deep learning research. Read on!

A common misconception is that the risk of overfitting increases with the number of parameters in the model. In reality, a single parameter suffices to fit most datasets: arxiv.org/abs/1904.12320 Implementation available at: github.com/Ranlot/single-…

My personal identity was hacked last week. The attacker was able to steal $100k+ in a sweep of my Coinbase account. I'm equal parts embarrassed, hurt, and deeply remorseful. In an effort to raise awareness about the attack, I wrote about it here: bit.ly/2VN5bZU

"Datasheets for Datasets," by @TimnitGebru, @JamieMmt, @BrianaVecchione, @JennWVaughan, @HannaWallach, @HalDaume3, and @KateCrawford, proposes that every dataset be accompanied with a datasheet that documents its provenance, uses, etc. bit.ly/3oMFq7E

Are you overwhelmed by everything happening in the ML ecosystem? We're doing a small crowdsourced initiative with a high-level distillation+timeline of cool big things happening in the ML landscape. Feel free to contribute! 🤗 github.com/osanseviero/ml…

Large language models have demonstrated a surprising range of skills and behaviors. How can we trace their source? In our new paper, we use influence functions to find training examples that contribute to a given model output.

A nice post about the various techniques used to get a training job to scale to more than 50,000 TPU v5e chips on Google Cloud. cloud.google.com/blog/products/…

Claude 2.1 (200K Tokens) - Pressure Testing Long Context Recall We all love increasing context lengths - but what's performance like? Anthropic reached out with early access to Claude 2.1 so I repeated the “needle in a haystack” analysis I did on GPT-4 Here's what I found:

Precisely

Democratizing Data at Airbnb j.mp/2sTWvOi

This book from 1847 describes geometric principles with colourful graphics publicdomainreview.org/collections/th… #OliverByrne

Bookmark: Tufte in R dlvr.it/PNL10z

⚡️ “Blockchains Will Replace Networks With Markets” by David J Phillips x.com/i/moments/8775…

Deep RL Bootcamp lecture videos and labs release sites.google.com/view/deep-rl-b…! :) [Organized by Pieter Abbeel, Peter Chen, Rocky Duan, Andrej Karpathy]

"Latency Numbers Every Programmer Should Know" It is hard for humans to get the picture until you translate it to "human numbers":

This is pretty neat! Formats Arxiv latex source into readable blog posts. arxiv-vanity.com

What do neural nets see? You may be surprised. Alex Mordvintsev @ludwigschubert & I explore. distill.pub/2017/feature-v…

False CSV assumptions donatstudios.com/Falsehoods-Pro…