Calculus is a hard subject and so I was a bit skeptical going into this book because of the title. After 4 pages in, I got hooked. Really fun book to learn or review important topics in Calculus. calculusmadeeasy.org

WoW 16 papers (!!) of ASPLOS 2024 are authored or co-authored by @IllinoisCS and Illinois ECE faculty and students from 9 research groups across 13 technical sessions. What a powerhouse of multidisciplinary computer systems research at UIUC.

Introducing OpenDevin CodeAct 1.0 - a new State-of-the-art open coding agent! It achieves a 21% unassisted resolve rate on SWE-Bench Lite, a 17% relative improvement above the previous SOTA by SWE-Agent. Check out our blog or the thread 🧵for more details: xwang.dev/blog/2024/open…

Hey, if you are at PyCon next week and are looking for a ~3h intro to PyTorch (incl. goodies like mixed-precision & multi-GPU training, and of course LLM finetuning), I'll be there ☺️ github.com/rasbt/pycon2024

We've added a comprehensive section on leveraging OSS-Fuzz to improve the security and stability of open-source projects to our testing handbook. Learn how to run fuzzing harnesses, extend them, and reproduce crashes. buff.ly/3KehFR6

Curriculum for Karpathy's new planned course is 🌶️ github.com/karpathy/LLM10…

With today’s launch of Llama 3.1, we release CyberSecEval 3, a wide-ranging evaluation framework for LLM security used in the development of the models. Additionally, we introduce and improve three LLM security guardrails. Summary in this 🧵, links to paper/github at bottom:

I just created a notebook using Llama 3.1 70B to generate a synthetic data for preference finetuning / aligning LLMs: github.com/rasbt/LLMs-fro… (The updated Llama license now allows using Llama 3.1 to improve other models, yay!). You can probably guess what comes next... 😊

READ: 130-page cheat sheet outlining key #MachineLearning concepts: bit.ly/130pgMLsheet

IBM devs release Bee Agent Framework, an open-source framework to build, deeply, and serve agentic workflows at scale. Features include: - Bee agents refined for Llama 3.1 - sandboxed code execution - flexible memory management for optimizing token usage - handling complex

Huge efforts to improve LLMs for tool use, computer use, reasoning, and long-context understanding. Here are a few interesting papers for the weekend: 1). Agentic Information Retrieval Provides an introduction to agentic information retrieval, which is shaped by the

the best researchers from Meta, Yale, Stanford, Google DeepMind, and Microsoft laid out all we know about Agents in a 264-page paper [book], here are some of their key findings:

New paper by University of Illinois tests the ability of agents to aid cybersecurity research: SEC-Bench. It tests both PoC input generation and automated vulnerability patching. HT Hwiwon Lee, Ziqi Zhang, Hanxiao Lu, Lingming Zhang