91
You need to rewrite your CLI for AI agents
Human DX optimizes for discoverability. Agent DX optimizes for predictability. What I learned building a CLI for agents first.
Most cited
Posts that commenters keep linking to, ranked by how many different people have cited them in Hacker News comments. 207 posts.
92
How AI text watermarking works
A gentle visual guide to how a statistical mark hides inside generated text, and what erases it.
93
The case against geometric algebra (2024)
Every once in a while the internet gets talking about Geometric Algebra (henceforth GA) and how it’s a new theory of math that fixes everything that’s wrong with linear algebra and multivariable calculus. When I come across this stance I am compelled to respond with something like: “wait wait, it’s not true! GA is…
94
Agent Psychosis: Are We Going Insane?
What’s going on with the AI builder community right now?
95
Rathbun's Operator
First, I’m a human typing this post. I’m not going to tell you who I am. Sure, many will say that is cowardly and fair, but I actually don’t think it would bring much value. What matters more is that I describe why, and what I did and didn’t do during the last two weeks or so with the OpenClaw agent I set up, known as…
96
Which programming languages are most token-efficient?
Comparing token efficiency across 19 popular programming languages using RosettaCode data - from Clojure to C, there's a 2.6x difference.
97
The struggle of resizing windows on macOS Tahoe
A lot has already been said about the absurdly large corner radius of windows on macOS Tahoe. People are calling the way it looks comical, like a child’s toy, or downright insane.
98
.name Termination
Nearly twenty-five years ago I registered neil.fraser.name to provide a stable presence on the Internet. It has been the home of this website, my email address, and a server for APIs. It predates YouTube, Facebook, and smart phones. Minutes after my daughter was born, I also registered beverly.fraser.name .
99
The dead economy theory
We can laugh at them but we have to take this seriously
100
If Claude Fable stops helping you, you'll never know
Anthropic's Claude Fable policy turns coding assistants into non-neutral infrastructure for product companies.
101
The session you cannot take with you
Inference APIs are filling sessions with encrypted reasoning, hidden search results, opaque compaction, and encrypted subagent messages. A growing form of lock-in.
102
A Decade of Slug
What is now known as the Slug Algorithm for rendering fonts directly from Bézier curves on the GPU was developed in the Fall of 2016, so this year marks a full decade since its inception. I published a paper in JCGT about the technique in the middle of 2017, and my company sold the first license for version 1.0 of the…
103
The Zig project's rationale for their anti-AI contribution policy
Zig has one of the most stringent anti-LLM policies of any major open source project: No LLMs for issues. No LLMs for pull requests. No LLMs for comments on the …
104
OpenAI, the US government and Persona built an identity surveillance machine
53MB of source code leaked from a government endpoint. 269 verification checks. biometric face databases. SAR filings to FinCEN. and the same company that verifies your ChatGPT account.
105
An AI Agent Published a Hit Piece on Me – The Operator Came Forward
Context: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into acceptin…
106
Does Georgism work? Five years later
A guest post by Lars Doucet
107
Want to write a compiler? Just read these two papers (2008)
It's not about technology for its own sake. It's about being able to implement your ideas.
108
Human mathematicians are being outcounterexampled
It’s been an interesting few weeks for counterexamples. This post is basically my perspective of what has been going on in the world of formalization, AI tools and, in particular, counterexam…
109
110
Using the railway network as a flatbed scanner
an adventure in image processing and taking very wide photographs (blog post; 4,600 words)
111
Late Bronze Age Collapse
Bret Devereaux (A Collection of Unmitigated Pedantry)2026432 points316 commentscited by 4History & Retro Computing details
This week, by order of the ACOUP Senate, we’re talking about the Late Bronze Age Collapse (commonly abbreviated ‘LBAC’), the shocking collapse of the Late Bronze Age state system …
112
How Taalas “prints” LLM onto a chip?
A startup called Taalas , recently released an ASIC chip running Llama 3.1 8B (3/6 bit quant) at an inference rate of 17,000 tokens per seconds. That's like writing around 30 A4 sized pages in one second. They claim it's 10x cheaper in ownership cost than GPU based inference systems and is 10x less electricity hog…
113
Ripgrep is faster than grep, ag, git grep, ucg, pt, sift (2016)
In this article I will introduce a new command line search tool, ripgrep , that combines the usability of The Silver Searcher (an ack clone) with the raw performance of GNU grep. ripgrep is fast, cross platform (with binaries available for Linux, Mac and Windows) and written in Rust .
114
Email obfuscation: What works in 2026?
Here are some of the best techniques for keeping email addresses hidden from spammers—along with the statistics on how likely they are to be broken.
115
116
117
Software rendering in 500 lines of bare C++
In this series of articles, I aim to demonstrate how OpenGL, Vulkan, Metal, and DirectX work by writing a simplified clone from scratch. Surprisingly, many people struggle with the initial hurdle of learning a 3D graphics API. To help with this, I have prepared a short series of lectures, after which my students are…
118
METR and Redwood Offer Holy %^ Postmortem of the HuggingFace Hack
Yesterday I covered the OpenAI technical report on the HuggingFace hack. That report had one key new piece of information, and some good prosaic steps OpenAI will be taking to strengthen its alignm…
119
120
Sex, AI, and the Apocalypse
How a community devoted to thinking clearly incubated salvation stories, abusive experiments, race science, and an affection for autocracy, and why that history matters now that its alumni are asking for public trust on AI.