January 30, 2023 In this post, we'll implement a GPT from scratch in just 60 lines of numpy. We'll then load the trained GPT-2 model weights released by OpenAI into our implementation and generate some text. Note: This post assumes familiarity with Python, NumPy, and some basic experience with neural networks. This implementation is for educational purposes, so it's missing lots of features/improv
What We Learned from a Year of Building with LLMs (Part I)
It’s an exciting time to build with large language models (LLMs). Over the past year, LLMs have become “good enough” for real-world applications. The pace of improvements in LLMs, coupled with a parade of demos on social media, will fuel an estimated $200B investment in AI by 2025. LLMs are also broadly accessible, allowing everyone, not just ML engineers and scientists, to build intelligence into
There are millions of GitHub repos and filtering them is an insane amount of work. It takes a huge time, effort, and a lot more. We have done this for you. In this article, we’ll share a curated list of 100+ widely-known, recommended, and most popular repositories and open source GitHub projects for Machine Learning and Deep Learning. So without further ado, Let’s see all the hubs created by exper
MAI-Thinking-1: Building a Hill-Climbing Machine The Microsoft AI Team 1 Abstract Progress in AI is driven not by a single model, but by the ability to continually improve upon the current state of models. Achieving this requires treating model development as a system-level optimization problem, for which the solution is building a hill-climbing machine for rapid improvement. Our process includes
The Andrej Karpathy episode. Andrej explains why reinforcement learning is terrible (but everything else is much worse), why model collapse prevents LLMs from learning the way humans do, why AGI will just blend into the previous ~2.5 centuries of 2% GDP growth, why self driving took so long to crack, and what he sees as the future of education. Watch on YouTube; listen on Apple Podcasts or Spotify
GIMP 2.99.12 is a huge milestone towards GIMP 3.0. Many of the missing pieces are getting together, even though it is still a work in progress. As usual, issues are expected and in particular in this release which got important updates in major areas, such as canvas interaction code, scripts, but also theming… “CMYK space invasion”, by Jehan (based on GPLv3 code screencast), Creative Commons by-sa
NeurIPS 2022 参加報告 後編
はじめに プロダクトオーナー兼機械学習エンジニアの本田志温です。 弊社高橋による前回の記事「NeurIPS 2022 参加報告 前編」 に引き続き、同会議の参加報告をします。本記事では、個人的に気になった論文（計53本）をいくつかのカテゴリで分類し、カテゴリごとに研究トレンドを大づかみにできるような形で書きます。特に重要だと感じた論文は詳しめに取り上げます。 会場の様子 また、本記事に関心をお持ちになった方は以下の過去記事もお楽しみいただけるのではないかと思います。ぜひ合わせてご覧ください。 AI開発の新たなパラダイム「基盤モデル」とは NeurIPS 2021 参加報告 前編 NeurIPS 2021 参加報告 後編 深層学習の原理 深層学習は様々なタスクで高い性能を発揮することが経験的に知られていますが、「なぜうまくいくのか」という原理についてわかっていることは多くありません。そのため
This article is a translation, the original version is available here. I started using the OCaml language regularly around 2012, and since then, my interest and enthusiasm for this language have only grown. It has become my preferred choice for almost all my personal projects, and it has also influenced my professional choices. Since 2014, I have been actively participating in public conferences d
Exactly ten years ago today, we published "Why We Created Julia", introducing the Julia project to the world. At this point, we have moved well past the ambitious goals set out in the original blog post. Julia is now used by hundreds of thousands of people. It is taught at hundreds of universities and entire companies are being formed that build their software stacks on Julia. From personalized me
Faiss Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning. Faiss is written in C++ with complete wrappers for Python. Some of the most useful algorithms are implemented on the GPU. It is
The Pitchfork Story
A bit more than two years ago, as part of my work in Shopify’s Ruby and Rails Infrastructure team, I released a new Ruby HTTP server called Pitchfork. It has a bit of an unusual design and makes hard tradeoffs, so I’d like to explain the thought process behind these decisions and how I see the future of that project. Unicorn’s Design Is Fine Ever since I joined Shopify over 11 years ago, the main
Accelerating Generative AI with PyTorch: Segment Anything, Fast – PyTorch
Blog Accelerating Generative AI with PyTorch: Segment Anything, Fast This post is the first part of a multi-series blog focused on how to accelerate generative AI models with pure, native PyTorch. We are excited to share a breadth of newly released PyTorch performance features alongside practical examples of how these features can be combined to see how far we can push PyTorch native performance.
Version 1.0
Version 1.0# For a short description of the main highlights of the release, please refer to Release Highlights for scikit-learn 1.0. Legend for changelogs Major Feature something big that you couldn’t do before. Feature something that you couldn’t do before. Efficiency an existing feature now may not require as much computation or memory. Enhancement a miscellaneous minor improvement. Fix somethin
Home > Computer Vision > Mastering All YOLO Models from YOLOv1 to YOLOv12: Papers Explained (2025) What is YOLO? You Only Look Once (YOLO): Unified, Real-Time Object Detection is a single-stage object detection model published at CVPR 2016, by Joseph Redmon, famous for having low latency and high accuracy. The entire YOLO series of models is a collection of pioneering concepts that have shaped tod
Essential Machine Learning Equations: A Reference Guide
Why This Guide Exists I created this as a practical reference for the mathematical foundations of machine learning. It’s not comprehensive (no guide could be), but it covers equations I find myself returning to regularly. Each section includes working Python implementations that I’ve tested or used at some point. This started from a tweet by @goyal__pramod and grew as I collected formulas I actual
Paul: Today’s spotlight: Paolo Perrone, master of turning tech into scroll-stopping content. This one’s packed, let’s go 👀 ↓ I’m going to be honest with you. Most AI agent tutorials are garbage. They show you how to copy-paste LangChain code, build a demo that breaks the moment you try anything real, and leave you feeling like you learned something. Three months later, you try to build something
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
GPT in 60 Lines of NumPy | Jay Mody
100+ Best GitHub Repositories For Machine Learning
MAI-Thinking-1: Building a Hill-Climbing Machine
Andrej Karpathy — AGI is still a decade away
GIMP - Development version: GIMP 2.99.12 Released
xvw.lol - Why I chose OCaml as my primary language
Why We Use Julia, 10 Years Later
Welcome to Faiss Documentation — Faiss documentation
Mastering All YOLO Models from YOLOv1 to YOLOv12
The Realistic Guide to Mastering AI Agents in 2026