5431
A stateful browser agent using self-healing DOM maps
Most browser agents forget what they’ve done. This one remembers, adapts, and learns, redefining how AI agents get work done.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 6,335 posts.
5432
OpenAI acquires Global Illumination
The entire team has joined OpenAI.
5433
Zero-Copy GPU Inference from WebAssembly on Apple Silicon
A WebAssembly module's linear memory can be shared directly with the Apple Silicon GPU: no copies, no serialization, no intermediate buffers. Here's how the zero-copy chain works, what we measured, and what it enables for stateful AI inference.
5434
Claude's Load-Bearing Seams
Now that I have the full picture, the load-bearing seams are much clearer. They are not merely incidental details around the edges. They materially change how the entire situation needs to be understood, and that is the smoking gun I should have recognized earlier.Claude's load-bearing seams
5435
PP-YOLO Surpasses YOLOv4 – State-of-the-art object detection techniques
Baidu publishes PP-YOLO and pushes the state of the art in object detection research by building on top of YOLOv3, the PaddlePaddle deep learning framework, and cutting edge computer vision research.
5436
The inefficiency of RL, and implications for RLVR progress
And implications for RLVR progress
5437
Evaluating LLMs for my personal use case
My life is not a math Olympiad
5438
CuPy Accelerates NumPy on the GPU? Hold My Cider, Here's Clojure
Everyone knows that Java is slow and Clojure is not a great choice for number crunching, but as soon as I dig anywhere with my software, I discover that the ...
5439
5440
Why OpenCV uses BGR color space (2015)
Learn the historical reason OpenCV stores color images in BGR order instead of RGB, from early camera formats to compatibility decisions.
5441
New Method for Compressing Neural Networks Better Preserves Accuracy
Get the latest news and features about smart home, Alexa Built-in, and Alexa Gadgets.
5442
How to put machine learning models into production
The goal of building a machine learning model is to solve a problem, and a machine learning model can only do so when it is in production and actively in use by consumers. As such, model deployment is as important as model building.
5443
Why Deep Learning Works II: the Renormalization Group
Deep Learning is amazing. But why is Deep Learning so successful? Is Deep Learning just old-school Neural Networks on modern hardware? Is it just that we have so much data now the methods work b…
5444
ML on Apple ][+
Success! There is machine learning happening on my Apple ][+.
5445
Introduction to Mean Shift Algorithm
Its been quite some time since I wrote a Data Mining post . Today, I intend to post on Mean Shift – a really cool but not very well known algorithm. The basic idea is quite simple but the results a…
5446
Regarding the Most Recent Amazon Mechanical Turk Data Contamination
Suggested Citation: Bai, H. (2018) Evidence that A Large Amount of Low Quality Responses on MTurk Can Be Detected with Repeated GPS Coordinates. Retrieved from: https://www.maxhuibai.com/blog/evidence-that-responses-from-repeating-gps-are-random
5447
Bringing Up DeepSeek-V4-Flash on AMD MI300X
A story of sharp edges, segfaults, and standards
5448
5449
5450
5451
Capsule Networks Explained
Assumed Knowledge: Convolutional Neural Networks, Variational Autoencoders Disclaimer: This article does not cover the mathematics behind Capsule Networks, but rather the intuition and motivation behind them. What are Capsule Networks and why do they exist? The Capsule Network is a new type of neural network…
5452
LLM-D: Kubernetes-Native Distributed Inference
Introducing llm-d: Kubernetes-native distributed LLM inference with KV-cache routing, disaggregated serving, and SOTA performance per dollar. Built on vLLM.
5453
Deep Learning in Clojure from Scratch to GPU: Learning a Regression
A great moment has arrived. We are going to apply our neural networks implementation to a regression problem. The network is going to learn a known function,...
5454
Clojure from Scratch to GPU: A Simple Neural Network Training API
The stage has been set for wrapping up the simplest version of a complete neural network API, and its key part that offers the entry for the /learning/ funct...
5455
How Cursor (AI IDE) Works
Turning LLMs into coding experts and how to take advantage of them.
5456
Context Engineering for AI Agents: Lessons
This post shares the local optima Manus arrived at through our own "SGD". If you're building your own AI agent, we hope these principles help you converge faster.
5457
The evolution of OpenAI's mission statement
As a USA 501(c)(3) the OpenAI non-profit has to file a tax return each year with the IRS. One of the required fields on that tax return is to “Briefly …
5458
5459
What if AI is a failed dream?
A collection of thoughts, ideas and unsolicited opinion from Made by Many: articles, reflections, talks and interviews from the people doing the work.
5460
MongoDB acquires Voyage AI
MongoDB to integrate Voyage AI's industry-leading embedding and reranking models, delivering highly accurate and relevant information retrieval to power sophisticated AI use cases NEW YORK , Feb. 24, 2025 /PRNewswire/ -- MongoDB, Inc. (NASDAQ: MDB), the leading database for modern applications,