4951
From text to token: How tokenization pipelines work
Understanding how search engines transform text into tokens through character filtering, tokenization, stemming, and stopword removal.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 6,335 posts.
4952
Wiki Builder: Skill to Build LLM Knowledge Bases
Wiki Builder is an open-source Claude Code plugin that turns the LLM-knowledge-base workflow into a one-command setup. Scaffold a configurable wiki, point Claude at sources, and let the agent compile durable pages, indexes, and concept maps for you.
4953
A New Book: Building Machine Learning Systems with Python
I wrote a book. Well, only in part. Willi Richert and I wrote a book. It is called Building Machine Learning Systems With Python and is now available from Amazon (or Amazon.co.uk), although it has …
4954
Foundations of ML and AI: Book recommendations
Here's what I recommend to programmers if they want to understand machine learning. Six fantastic books that you can work with in your spare time to build yo...
4955
Build a Deep Learning Library
Instead of just learning how to use a deep learning library, we are going to learn how to create one.
4956
Open sourcing Embedding Projector: a tool for visualizing high dimensional data
Posted by Daniel Smilkov and the Big Picture group Recent advances in Machine Learning (ML) have shown impressive results, with applications rangin...
4957
The What-If Tool: Code-Free Probing of Machine Learning Models (2018)
Posted by James Wexler, Software Engineer, Google AI Building effective machine learning (ML) systems means asking a lot of questions. It's not eno...
4958
Interpretable Machine Learning Through Teaching
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
4959
Using secondary school maths to demystify AI
Educators can show in secondary school maths that AI systems don’t think, making maths more interesting while teaching core concepts of AI.
4960
AI companies are pivoting from creating gods to building products
Turning models into products runs into five challenges
4961
4962
LLMs could be, but shouldn't be compilers
I’ve been going round and round in my mind about a particular discussion around LLMs: are they really similar to compilers? Are we headed toward a world where people don’t look at the underlying code for their programs?
4963
Slack's core flaws require topic modeling to fix
Chatops is a ladder
4964
Something Big Is Happening
A personal note for the non-tech people in my life on what AI is starting to change — why it's moving faster than you think, and what to do about it.
4965
The Decade of Deep Learning
As the 2010’s draw to a close, it’s worth taking a look back at the monumental progress that has been made in Deep Learning in this decade.[1] Driven by the development of ever-more powerful comput
4966
AI Content Generation, Part 1: Machine Learning Basics
This technology is already changing the creative industry. Here's how it works.
4967
Machine learning systems are stuck in a rut
Machine learning systems are stuck in a rut Barham & Isard, HotOS’19 In this paper we argue that systems for numerical computing are stuck in a local basin of performance and programmabil…
4968
Here lies the internet, murdered by generative AI
Corruption everywhere, even in YouTube's kids content
4969
4970
New algorithm flies drones faster than human racing pilots
Das Team Media Relations steht Journalistinnen und Journalisten gerne zur Verfügung. Suchen Sie unsere Expertinnen und Experten direkt, finden Sie Bilder der UZH und Medienberichte oder kontaktieren Sie Ihre Medien-Ansprechpartner.
4971
4972
Clio: A system for privacy-preserving insights into real-world AI use
Anthropic's new system, Clio, analyzes how people use AI while maintaining their privacy.
4973
The PlanetScale vectors public beta
You can now use the vector data type for vector search and storage in your PlanetScale MySQL database.
4974
4975
Compiling ML models to C for fun
We make micrograd fly with a little compiler magic. In this post, we’ll write a ML compiler from scratch.
4976
Diffusion with Offset Noise: Finetuning SD to generate very dark or light images
Historical research record. Fine-tuning against a modified noise, enables Stable Diffusion to generate very dark or light images easily.
4977
Neuralink and the Brain's Magical Future
I knew the future would be shocking but this is a whole other level.
4978
Absolute Zero Reasoner
Current reasoning models trained with Reinforcement Learning with Verifiable Rewards (RLVR) often rely on manually curated datasets, raising scalability concerns and potentially limiting future AI growth beyond human-defined tasks. To address this, we propose the Absolute Zero paradigm, where a single model…
4979
Techniques for Training Large Neural Networks
Large neural networks are at the core of many recent advances in AI, but training them is a difficult engineering and research challenge which requires orchestrating a cluster of GPUs to perform a single synchronized calculation.
4980
AIs Named by AIs
Neural networks can be good at naming things, I’ve discovered. Recently I’ve been experimenting with a neural network called GPT-2, which OpenAI trained on a huge chunk of the internet. Thanks to a colab notebook implementation by Max Woolf, I’m able to fine-tune it on specific lists of data -