931
MCP is dead; long live MCP
Understanding the social media zeitgeist around CLIs and the premature death of MCP
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 3,091 posts.
932
Stochastic gradient descent written in SQL
Edit – this post generated a few insightful comments on Hacker News. I’ve also put the code in a notebook for ease of use. Introduction Modern MLOps is complex because it involves too many components. …
933
Designing NotebookLM
Designer, builder, and visual storyteller. Now building Huxe. Previously led design on NotebookLM and contributed to Google AI projects like Gemini and Search. Also shoot photo/video for brands like Coachella, GoPro, and Rivian.
934
935
Understanding Transformers Using a Minimal Example
Visualizing the internal state of a Transformer model
936
Text Is All You Need
Personhood appears to be simpler than we thought
937
Why do we need human mathematicians anymore?
[This is a guest post by Po-Shen Loh, crossposted from his blog, where an illustrated version appears. This blog post was initially written in a different file format and converted using AI. —…
938
Certified 100% AI-free organic content
This is a last call to introduce a "made by an organically-sourced human" label.
939
We should revisit literate programming in the agent era
Literate programming is the idea that code should be intermingled with prose such that an uninformed reader could read a code base as a narrative, and come away with an understanding of how it works and what it does. Although I have long been intrigued by this idea, and have found uses for it in a couple1 of different…
940
RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8
Dual GPU setup: run Qwen 3.6 27B at a Q8 quantization at 80+ tokens/sec with 39GB total VRAM
941
Patrick Winston Explains Deep Learning
Patrick Winston is one of the greatest teachers at M.I.T., and for 27 years was Director of the Artificial Intelligence Laboratory (which later became part of CSAIL ).
942
GPT-3
May 2020 Gwern.net newsletter: GPT-3 scaling, implications, deep theory; anime GAN updates, and 1 book review.
943
I used GPT to build a search tool for my second brain note-taking system
In this post, I discuss how I used GPT embeddings to build a smart search tool for my second brain note-taking system.
944
Augmented reality with Python and OpenCV
You may (or may not) have heard of or seen the augmented reality Invizimals video game or the Topps 3D baseball cards. The main idea is to render in the screen of a tablet, PC or smartphone a 3D mo…
945
946
I gave Claude access to my pen plotter
I gave Claude Code access to my pen plotter. Not directly. I was the interface between the two machines. Claude Code produced SVG files that I plotted with my pen plotter. With my smartphone I captured photos that I pasted into the Claude Code session, asking Claude what it thought about the pictures. In total, Claude…
947
The RAG Obituary: Killed by agents, buried by context windows
I’ve been working in AI and search for a decade. First, I built Doctrine, the largest European legal search engine, and now I am building Fintool , an AI-powered financial research platform that helps institutional investors analyze companies, screen stocks, and make investment decisions.
948
Python vs. Rust for Neural Networks
Comparing a simple neural network in Rust and Python
949
Fun with Snapchat's Gender Swapping Filter
Snapchat's new gender-bending filter is a source of endless fun and laughs at parties. The results are very pleasing to look at. As someone ...
950
Andrej Karpathy talks about "Claws"
Andrej Karpathy tweeted a mini-essay about buying a Mac Mini ("The apple store person told me they are selling like hotcakes and everyone is confused") to tinker with Claws: I'm …
951
AI Meets WinDBG
Because manually squinting at hex dumps is so last century. Let me show you how AI-assisted debugging is leaving WinDBG's command line in the dust.
952
How Bayesian Inference Works (2016)
Bayesian inference is a way to get sharper predictions from your data. It’s particularly useful when you don’t have as much data as you would like and want to juice every last bit of predictive strength from it.
953
954
Creating a landing page using AI tools and no code
A step-by-step guide to making a landing page with AI and no-code tools: AI-written code and copy, fonts, colour palettes, images, audio and video.
955
Zen and the Art of Machine Learning Research
if you want to do world-class research, temperament matters more than talent
956
I Resurrected “Ugly Sonic” with Stable Diffusion Textual Inversion
The true dystopia of AI is that it can make Ugly Sonic look cool.
957
One model to learn them all
One model to learn them all Kaiser et al., arXiv 2017 You almost certainly have an abstract conception of a banana in your head. Suppose you ask me if I’d like anything to eat. I can say the word ‘…
958
Autocomplete as an Interface (2015)
the real reason zsh beats bash • how I got twice as fast in python • autocompleting all the things • maximizing user-interface bandwidth
959
What Google Translate can tell us about vibecoding
There has been rather a lot of doomsaying (and perhaps astroturfing) lately about LLMs as the end of computer programming. Much of the discussion has been lacking nuance, so I’d like to add mine. I see claims from one side that “I used $LLM_SERVICE_PROVIDER to make a small throwaway tool, so all programmers will be…
960
How to use Claude Code subagents to parallelize development
Updated 2026-07-10 for the agent-teams era. Originally published September 2025. A subagent in Claude Code is a separate agent your session spawns to do a...