2611
Optimizing Tool Selection for LLM Workflows with Differentiable Programming
How local, learnable routers can reduce token overhead, lower costs, and bring structure back to agentic workflows.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 3,092 posts.
2612
Backpropogation Is Just Steepest Descent with Automatic Differentiation (2013)
Preface The intended audience of this article is someone who knows something about Machine Learning and Artifical Neural Networks (ANNs) in particular and who recalls that fitting an ANN required a…
2613
Training Deep Networks with Data Parallelism in Jax
Misha Laskin personal website. Includes a blog and projects focused on artifical intelligence.
2614
2615
2616
2617
ChatLZMA – text generation from data compression
I came across a random tweet, found a Wikipedia page and bumped into some smart people and long story short, apparently compression is equivalent to general intelligence.
2618
Fast Tensors in Clojure – A Sneak Peek
There's a lot going on behind the scenes, since I am not only writing the books; at the same time I have to create the software to write about. For example, ...
2619
Making my local LLM voice assistant faster and more scalable with RAG
If you read my previous blog post, you probably already know that I like my smart home open-source and very local, and that certainly includes any voice assistant I may have. If you watched the video demo, you have probably also found out that it’s… slow. Trust me, I did too. Prefix caching helps, but it feels like…
2620
2621
Deep Learning, NLP, and Representations
neural networks , deep learning , representations , NLP , recursive neural networks
2622
I am leaving the AI party after one drink
Personal website of Lara Aigmüller. Thoughts about web frontend development, music, and more…
2623
AI researchers debate how close we are to recursive self-improvement
“We're nowhere near the ceiling.”
2624
The Token Compression Illusion: Why I'm Skeptical of RTK
RTK promises dramatic token savings for coding agents, but raw terminal compression is not the same as cheaper, safer, or more accurate software engineering.
2625
Are Humans Intelligent? An AI Op-Ed
After seeing so many people debate whether computers can be intelligent I thought it only fair to ask an AI. As with previous posts, I picked the best responses, but everything after the bolded pro…
2626
CS240 AI Cheating Retrospective
Jeff Turkstra's personal website. Contains photographs, memoirs, TI-86 & TI-89 programs/games, quotes, MIDI's, SeaQuest images, links, and more!
2627
Against the Dark Forest
The complex of ideas I’m going to call the Dark Internet Forest emerges from mostly insidery tech thinking, but from multiple directions.
2628
Giving GPT “Infinite” Knowledge
How to give GPT access to large amounts of data
2629
Declarative Programming with AI/LLMs
What Is Declarative Programming Broadly speaking, there are two ways to program/instruct a computer to perform a task, they are imperative...
2630
2631
Life Lessons from Machine Learning
What comes to mind when you hear the term “Machine Learning”? A bunch of programmers hunched over their computers in a dark room, working on something completely virtual & divorced from reality…
2632
2633
Adventures in Symbolic Algebra with Model Context Protocol
Personal blog of Stephen Diehl - Software engineer writing about technology, programming, and the future
2634
Reproducing DeepSeek's MHC: When Residual Connections Explode
DeepSeek replaced standard residuals with massive Hyper-Connections, and then watched them explode. I reproduced the 9x signal amplification to understand their fix: the Sinkhorn-Knopp algorithm. Part 1 of 2.
2635
2636
Towards the Cutest Neural Network
I recently needed to use a microcontroller to estimate the pose (translation and orientation) of an object using readings from six different sensors. Since the readings were non-linear and coupled with each other, an explicit analytical solution was out of the question.
2637
Training a 3.8B LLM to 0.384 CORE for $998
A 3.8B model pretrained from scratch to 0.384 CORE on 65B tokens in 43 hours, for $998.
2638
An Overview of Bayesian Inference (2019)
A few weeks ago I wrote about Kuhn’s theory of paradigm shifts and how it relates to Bayesian inference. In this post I want to back up a little bit and explain what Bayesian inference is, and eventually rediscover the idea of a paradigm shift just from understanding how Bayesian inference works.
2639
2640
