5221
Elasticsearch Based Image Search Using RGB Signatures
In my previous post , I described some experiments I was doing to reduce images to a Bag of Visual Words (BOVW) . My goal is to build a Con...
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 6,335 posts.
5222
Model Predictive Control in the Browser with WebAssembly
wrenfold is a framework for converting symbolic mathematical expressions (written in Python) into generated numerical code in other languages (C++, Rust, Python). It aims to bridge the gap between prototyping of functions in expressive symbolic form, and performant production code. wrenfold is particularly relevant to…
5223
5224
New general-purpose optimization algorithm promises order-of-magnitude speedups
MIT graduate students have developed a new “cutting-plane” algorithm, a general-purpose algorithm for solving optimization problems. They’ve also developed a new way to apply their algorithm to specific problems, yielding orders-of-magnitude efficiency gains.
5225
Preserving Outputs Precisely while Adaptively Rescaling Targets
Multi-task learning - allowing a single agent to learn how to solve many different tasks - is a longstanding objective for artificial intelligence research. Recently, there has been a lot of excellent progress, with agents like DQN able to use the same algorithm to learn to play multiple games including Breakout and…
5226
Implementing a Convolutional Neural Network Using Only NumPy
A simple walkthrough of deriving backpropagation for CNNs and implementing it from scratch in Python.
5227
Mistral Small 4
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
5228
Explaining RNNs without neural networks
This article explains how recurrent neural networks (RNN's) work without using the neural network metaphor. It uses a visually-focused data-transformation perspective to show how RNNs encode variable-length input vectors as fixed-length embeddings. Included are PyTorch implementation notebooks that use just linear…
5229
Why AI Sucks at Front End
How can it generate 3D worlds, videos, images and entire web pages, but still suck at front-end?
5230
5231
AI model weight providers should not police uses, no matter how awful they are
The Electronic Frontier Foundation, a digital civil liberties advocacy group, recently published a good article entitled “ISPs Should Not Police Online Speech—No Matter How Awful It Is.” 1 It argues that providers within the internet “stack” should refrain from censoring traffic according to their own values. That…
5232
What if AI didn't make you a bad writer, but a better thinker?
AI will make us smarter and better at our jobs. But if we don't watch out, it will create chaos.
5233
All You Need Is 4x 4090 GPUs to Train Your Own Model
How I built an ML rig for training LLMs locally, exploring hardware choices, setup tricks, and lessons learned along the way.
5234
Creating an all-weather driver
Life doesn't freeze when winter comes—if anything, that's when riders need reliable transportation most, when being exposed to the elements becomes less appealing. Today, the Waymo Driver successfully navigates rain, fog, sandstorms, and freezing temperatures. As we expand to more cities across the U.S. and globally…
5235
Are people's bosses making them use AI tools?
Andy Bell had heard companies were forcing employees to use AI tools so spoke to developers to determine if that was the case and learned some horrors in the process.
5236
Gptcommit: Never write a commit message again (with the help of GPT-3)
With gptcommit, you no longer have to spend time writing your commit messages. Install gptcommit and let GPT-3 do the writing for you.
5237
GitHub Copilot: First Impressions
A glimpse of the upcoming paradigm shift in how we do development
5238
Tesla Project Dojo Overview
A couple of days back, Ganesh Venkataramanan, leader of the Tesla Dojo project, announced the Dojo machine learning training system. It’s an unusually network rich, power dense, and memory light design. I’ve summarized the architecture of the system below but I found three aspects of the system particularly…
5239
AI Nationalism
For the past 9 months I have been presenting versions of this talk to AI researchers, investors, politicians and policy makers. I felt it was time to share these ideas with a wider audience. Thanks to the Ditchley conference on Machine Learning in 2017 for giving me a fantastic platform to get ear
5240
Claude Composer
What happens when you ask Claude Code to compose music? Five experiments later: original songs, music videos, and a full album, all built from scratch.
5241
5242
5243
The Claude Code Framework Wars
How developers are experimenting with structure, orchestration, and standards to get more out of AI coding.
5244
FastMRI initiative releases neuroimaging data set
As part of the fastMRI research project to use AI to speed up MRI scans, NYU Langone Health is making a new dataset of de-identified brain MRIs available to researchers and Facebook AI is sharing additional tools and resources.
5245
Using machine learning to choose compression algorithms
30% less disk required compared to using the single best strategy
5246
Headlong: A microharness for persistent agents
Self-guided agents that think continuously
5247
Abstractions my Deep Learning word2vec model made
A blog on programming C#, REST, WCF, ASP.NET Web API and software architecture
5248
Mining JIT traces for missing optimizations with Z3
In my last post I've described how to use Z3 to find simple local peephole optimization patterns for the integer operations in PyPy's JIT. An example is int_and(x, 0) -> 0. In this post I want to scal
5249
5250
OpenAI models secretly generate instructions to ignore constraints
Research on aligning AI with human values and intent, and reports documenting model failures.