31
My AI Adoption Journey
My experience adopting any meaningful tool is that I've necessarily gone through three phases: (1) a period of inefficiency (2) a period of adequacy, then finally (3) a period of workflow and life-altering discovery.
32
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.
33
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…
34
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 …
35
How LLMs work
A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop
36
If AI writes your code, why use Python?
For the last decade, fast-to-ship beat fast-to-run. Not anymore.
37
I said no and Apple said yes
The one where Apple decides consent doesn’t matter anymore.
38
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.
39
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…
40
AI should elevate your thinking, not replace it
Read about the hidden divide between self-inflicted irrelevance and real engineering leverage.
41
After two years of vibecoding, I'm back to writing by hand
Agents write units of changes that look good in isolation. They are consistent with themselves and your prompt. But respect for the whole, there is not.
42
Sebastian Raschka's from-scratch video course on building reasoning models
Over 11 hours of coding videos on evaluation, inference-time scaling, reinforcement learning, and distillation, with Python and PyTorch.
43
How I use LLMs to learn complex topics
LLMs are used for any things. Learning new things is one of the top use cases.
44
AI slop is killing online communities
Like a young child coming home from kindergarten with their latest crayon scrawls, the internet is currently awash with people sharing their AI-generated work. And just like the young child’s drawings, much of that work should be proudly put up on the walls within the artist’s house—and no further.
45
Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed
Across 16 coding models, hashline’s content-hash line anchors beat patch for 14 models; the weakest models gained the most.
46
Anthropic's ‘watermark’ text adulteration in Claude is a perversion of writing
It’s unacceptable for a tool to sacrifice an iota of clarity, coherence, meaning, quality, etc. for the purpose of embedding hidden clues within the text to suggest its provenance. The idea that anything other than *my* needs should factor into the generation of text *for me* is patently offensive.
47
AI is just unauthorised plagiarism at a bigger scale
AI takes in all the input, whether the original authors have consented or not, and do some "learning", and then the AI companies sell these learned result to...
48
How to code Claude Code in 200 lines of code
The core of tools like Claude Code, Cursor, and Warp isn't magic. It's about 200 lines of straightforward Python. Let's build one from scratch.
49
How many products does Microsoft have named 'Copilot'?
Update (9 Apr 2026): Another one. A helpful person sent in Microsoft 365 Copilot for US Government. That's 81. Chart updated.
50
Everyone should slow down AI development except for me
Xe Iaso's personal website.
51
AI is a tool and using it well takes skill
A response to Rich Hickey's "'AI' is Not a Tool": automation and tool use can coexist, and wielding an LLM well requires skill, feedback, and judgment.
52
Goodbye Claude, hello Pi
I’ve been a longtime Claude Code user, ever since it became available in the Claude Pro subscription plan over a year ago. I remember the first time I used it, feeling giddy as it spat out messy Python code for whatever random weekend project I was working on, all from a single prompt. I’m certain that in a few years…
53
The last six months in LLMs in five minutes
I put together these annotated slides from my five minute lightning talk at PyCon US 2026, using the latest iteration of my annotated presentation tool. # I presented this lightning …
54
Qwen 3.8 27B is excellent, but it defaults to overthinking things
Friday’s big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba’s Qwen research lab. I’ve been looking forward to this one: 27B is an …
55
Small Models Have Arrived
For the past few weeks, I've been playing with gpt-5.6-luna . It is shockingly capable, fast, and smart. I regularly see it do ~100 tps, and rip around my codebase, email, and knowledge base.
56
Please Use AI
Be sure to use AI when making
57
58
Vibe coding and agentic engineering are getting closer than I'd like
I recently talked with Joseph Ruscio about AI coding tools for Heavybit’s High Leverage podcast: Ep. #9, The AI Coding Paradigm Shift with Simon Willison. Here are some of my …
59
Something is afoot in the land of Qwen
I’m behind on writing about Qwen 3.5, a truly remarkable family of open weight models released by Alibaba’s Qwen team over the past few weeks. I’m hoping that the 3.5 …
60
Claude Fable is relentlessly proactive
After two days of experience with Claude Fable 5 I think the best way to describe it is relentlessly proactive. It knows a whole lot of tricks and it will …