The latest blog posts to take off on Hacker News. 3,091 posts.
Over the past two years I’ve quietly rebuilt major parts of the OldNYC photo viewer . The result: 10,000 additional historic photos on the map , more accurate locations, and a site that’s cheaper and easier to run—thanks to modern AI tools and the OpenStreetMap ecosystem.
As the eleventh hour dawns all the pieces start to fall into place. I lived my life knowing this would happen, yet when it is I may be just as unprepared as anyone else. As any self driving car maker knows, predicting doesn’t mean you can act.
Web developer and cybersecurity researcher
LM Studio 0.4.0 introduced llmster and the lms CLI. Here is how I set up Gemma 4 26B for local inference on macOS that can be used with Claude Code.
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 …
Update (9 Apr 2026): Another one. A helpful person sent in Microsoft 365 Copilot for US Government. That's 81. Chart updated.
How coding agents use tools, memory, and repo context to make LLMs work better in practice
What the accidental Claude Code source code leak tells us about the real value of code, product market fit, and why integration is what actually makes software great.
You may already be aware of John Baez’s “Crackpot Index” , which provides a simple tongue-in-cheek scoring system for assessing whether a research contribution to physics is likely “revolutionary.” The list contain such gems as “40 points for comparing yourself to Galileo, suggesting that a modern-day Inquisition is…
The one where I pack up my bags.
Anthropic accidentally shipped a source map in their npm package, exposing the full Claude Code source. Here's what I found inside.
When you write a document or essay, you are posing a question and then answering it. For example, a PRD answers the question, “What should we build?” A technical spec answers, “How should we build it?” Sometimes the question is more difficult to answer—“What are we even trying to accomplish?” And with every attempt at…
The catalysts for a crash are already laid out, and it can happen sooner than most expect. AI is here to stay. If used right, chances are it will make us all more productive. That, on the other hand, does not mean it will be a good investment. Big tech doesn’t need to win, just outspend Magnificent 7 companies are…
Why the HJB is Bellman's equation in continuous time, why continuous time matters, and how to solve the resulting control problem with neural policy iteration.
After a team member summoned Copilot to correct a typo in a PR of mine, Copilot edited my PR description to include and ad for itself and Raycast .
I've been vibe-coding a lot lately. Like, a lot a lot
How TurboQuant compresses the KV cache without losing accuracy, and what that could mean for memory stocks
How the KV cache gives every AI conversation a physical weight in silicon, and what happens when the memory runs out.
Lzon.ca. A personal blog, by a programmer and IT expert.2026216 points144 commentsAI & Machine Learning details
A personal blog, by a programmer and IT expert. Essays, Articles, Guides, and Recipes. As well as Code, Quotes, and Links.
Executives love AI while ICs stay skeptical. The divide comes down to non-determinism: who is evaluated on judgment versus deterministic execution.
Personal website of Lara Aigmüller. Thoughts about web frontend development, music, and more…
What if you could let Claude and Codex work together as pair programmers, talking to each other directly? One of them as the main worker and the other as a reviewer.
Hi! If you like this piece and want to support my independent reporting and analysis, why not subscribe to my premium newsletter? It’s $70 a year, or $7 a month, and in return you get a weekly newsletter that’s usually anywhere from 5000 to 18,000 words, including
For two centuries, the credential system gave intelligence a route to heritable capital. Artificial intelligence is closing that route. This essay builds the argument from first principles - with probability theory, interactive simulations, and a prediction specific enough to be falsifiable - and puts a number on the…
In Part 1, I described how duplicating a block of seven middle layers in Qwen2-72B — no weight changes, no training — produced the #1 model on the HuggingFace Open LLM Leaderboard. The method, which I called RYS (Repeat Your Self), was discovered using nothing but hard math probes and EQ-Bench on a pair of RTX 4090s.
A few months ago I was tasked with creating an internal tool for the company's engineers: a Chat that used a local LLM. Nothing extraordinary so far…
Yogesh Kumar's personal website
Any sufficiently complicated AI system contains an ad hoc, informally-specified, bug-ridden implementation of half of DSPy.
Learn how I built an ai receptionist for my brother's mechanic shop
