61
Enough AI copilots, we need AI HUDs
In my opinion, one of the best critiques of modern AI design comes from a 1992 talk by the researcher Mark Weiser where he ranted against “copilot” as a metaphor for AI.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 3,090 posts.
62
How I use Claude Code: Separation of planning and execution
The research-plan-implement workflow I use to build software with Claude Code, and why I never let it write code until I've approved a written plan.
63
I cancelled Claude: Token issues, declining quality, and poor support
Prefix Note As this post is gaining more attention than expected on HN, I want to make some things clear - although I thought they are obvious. It sounds like a rant about Claude’s quality in general - if you don’t read to the end. But my concerns are more focused on the support performance and token issues - fully…
64
Building LLMs from the Ground Up: A 3-Hour Coding Workshop
If your weekend plans include catching up on AI developments and understanding Large Language Models (LLMs), I've prepared a 1-hour presentation on the development cycle of LLMs, covering everything from architectural implementation to the finetuning stages.
65
Please don't mention AI again
The recent innovations in the AI space, most notably those such as GPT-4, obviously have far-reaching implications for society, ranging from the utopian eliminating of drudgery, to the dystopian damage to the livelihood of artists in a capitalist society, to existential threats to humanity itself.
66
Everyone in Seattle hates AI
A post about everyone in Seattle hating AI.
67
The last six months in LLMs, illustrated by pelicans on bicycles
I presented an invited keynote at the AI Engineer World’s Fair in San Francisco this week. This is my third time speaking at the event—here are my talks from October …
68
Eight years of wanting, three months of building with AI
For eight years, I’ve wanted a high-quality set of devtools for working with SQLite. Given how important SQLite is to the industry1, I’ve long been puzzled that no one has invested in building a …
69
Things that helped me get out of the AI 10x engineer imposter syndrome
Curing Your AI 10x Engineer Imposter Syndrome
70
How LLMs work
A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop
71
2025: The Year in LLMs
This is the third in my annual series reviewing everything that happened in the LLM space over the past 12 months. For previous years see Stuff we figured out about …
72
Using Claude Code to modernize a 25-year-old kernel driver
As a bit of background, one of my hobbies is helping people recover data from old tape cartridges, such as QIC-80 tapes, which were a rather popular backup medium in the 1990s among individuals, small businesses, BBS operators, and the like. I have a soft spot for tape media; there’s something about the tactile…
73
74
If AI writes your code, why use Python?
For the last decade, fast-to-ship beat fast-to-run. Not anymore.
75
How I program with LLMs
This document is a summary of my personal experiences using generative models while programming over the past year. It has not been a passive process. I have intentionally sought ways to use LLMs while programming to learn about them. The result has been that I now regularly use LLMs while working and I consider their…
76
The new skill in AI is not prompting, it's context engineering
Context Engineering is the new skill in AI. It is about providing the right information and tools, in the right format, at the right time.
77
78
The Unreasonable Effectiveness of Recurrent Neural Networks
Musings of a Computer Scientist.
79
NotebookLM's automatically generated podcasts are surprisingly effective
Audio Overview is a fun new feature of Google’s NotebookLM which is getting a lot of attention right now. It generates a one-off custom podcast against content you provide, where …
80
81
Gemini Diffusion
Another of the announcements from Google I/O yesterday was Gemini Diffusion, Google's first LLM to use diffusion (similar to image models like Imagen and Stable Diffusion) in place of transformers. …
82
Search tool that only returns content created before ChatGPT's public release
https://slopevader.com/ A search tool and browser extension for avoiding AI slop. Available for Chrome or Firefox. The tool filters web...
83
Nano Banana can be prompt engineered for nuanced AI image generation
Nano Banana allows 32,768 input tokens and I’m going to try to use them all dammit.
84
I said no and Apple said yes
The one where Apple decides consent doesn’t matter anymore.
85
Superintelligence: The Idea That Eats Smart People
This is the text version of a talk I gave on October 29, 2016, at Web Camp Zagreb [ video ] (45 mins)
86
Opus 4.5 is not the normal AI agent experience that I have had thus far
Three months ago I would have dismissed claims that AI could replace developers. Today, after using Claude Opus 4.5, I believe AI coding agents can absolutely replace developers.
87
How accurate have Ed Zitron's AI skeptic predictions been?
I was curious how well the predictions of the most widely cited AI skeptic I've seen (Ed Zitron) have done, so I looked at how his predictions panned out. To disclose my own biases, I've never had a particularly strong pro or anti AI progress position. For example, in 2022, I did a comprehensive look at predictions…
88
Stable Diffusion is a big deal
If you haven’t been paying attention to what’s going on with Stable Diffusion, you really should be. Stable Diffusion is a new “text-to-image diffusion model” that was released to the …
89
I replaced Animal Crossing's dialogue with a live LLM by hacking GameCube memory
Picture Tom Nook greeting you with a sentence nobody at Nintendo wrote. That is what “animal crossing llm” usually points to: an experimental fan…
90
AI should elevate your thinking, not replace it
Read about the hidden divide between self-inflicted irrelevance and real engineering leverage.