121
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.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 1,518 posts.
122
OpenCV 5 Is Here: The Biggest Leap in Years for Computer Vision
OpenCV 5 is here! A massive modernization brings a graph-based DNN engine, over 80% ONNX coverage, hardware acceleration, LLM/VLM support, and a faster Python-first core. Learn why this isn't just an incremental update.
123
Every Mac comes with an (undocumented) family member classifier
Every Mac since macOS 13 (2022) ships a pair of daemons whose only purpose in life is to build a graph about who you are, who you know, how those people are related to you and to each other, how you communicate with them, where you go, what you do and when. In this post, we look into how this system works and give you…
124
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.
125
Mistral raises €3B
Mistral today announced that it has raised €3 billion in a Series D funding round at a post-money valuation of more than €21 billion.
126
The path to ubiquitous AI (17k tokens/sec)
By Ljubisa Bajic Many believe AI is the real deal. In narrow domains, it already surpasses human performance. Used well, it is an unprecedented amplifier of human ingenuity and productivity. Its widespread adoption is hindered by two key barriers: high latency and astronomical cost. Interactions with language models…
127
How I use LLMs to learn complex topics
LLMs are used for any things. Learning new things is one of the top use cases.
128
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.
129
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.
130
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.
131
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...
132
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.
133
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.
134
Everyone should slow down AI development except for me
Xe Iaso's personal website.
135
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.
136
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…
137
The Codex App
Introducing the Codex app for macOS—a command center for AI coding and software development with multiple agents, parallel workflows, and long-running tasks.
138
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 …
139
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 …
140
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.
141
142
Please Use AI
Be sure to use AI when making
143
144
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 …
145
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 …
146
Leanstral: Open-source agent for trustworthy coding and formal proof engineering
The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.
147
Prism
Prism is a free LaTeX-native workspace with GPT-5.2 built in, helping researchers write, collaborate, and reason in one place.
148
Claude discovers a novel enzyme system with CRISPR-like repeats
In early results from our new life sciences research lab, Claude agents found an enzyme system whose function is still unknown.
149
Grok 4.5
Grok 4.5 is SpaceXSI's smartest model built for coding, agentic tasks, and knowledge work.
150
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 …