1141
The Claude Code Source Leak: fake tools, frustration regexes, undercover mode
Anthropic accidentally shipped a source map in their npm package, exposing the full Claude Code source. Here's what I found inside.
New
The latest blog posts to take off on Hacker News. 6,326 posts.
1142
Ollama is now powered by MLX on Apple Silicon in preview
Today, we're previewing the fastest way to run Ollama on Apple silicon, powered by MLX, Apple's machine learning framework.
1143
Do your own writing
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…
1144
How the AI Bubble Bursts
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…
1145
Hamilton-Jacobi-Bellman Equation: Reinforcement Learning and Diffusion Models
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.
1146
Copilot edited an ad into my PR
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 .
1147
Coding agents could make free software matter again
I've been vibe-coding a lot lately. Like, a lot a lot
1148
What if AI doesn't need more RAM but better math?
How TurboQuant compresses the KV cache without losing accuracy, and what that could mean for memory stocks
1149
From 300KB to 69KB per Token: How LLM Architectures Solve the KV Cache Problem
How the KV cache gives every AI conversation a physical weight in silicon, and what happens when the memory runs out.
1150
The first 40 months of the AI era
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.
1151
1152
Why are executives enamored with AI, but ICs aren't?
Executives love AI while ICs stay skeptical. The divide comes down to non-determinism: who is evaluated on judgment versus deterministic execution.
1153
I am leaving the AI party after one drink
Personal website of Lara Aigmüller. Thoughts about web frontend development, music, and more…
1154
Agent-to-agent pair programming
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.
1155
We rewrote JSONata with AI in a day, saved $500k/year
Learn how AI was used to rewrite JSONata into a faster Go library, reducing costs and improving data processing performance.
1156
Updates to GitHub Copilot interaction data usage policy
From April 24 onward, interaction data from Copilot Free, Pro, and Pro+ users will be used to train and improve our AI models unless they opt out.
1157
Quantization from the Ground Up
A complete guide to quantization: how LLMs store parameters as floats, why shrinking them to 4 or 8 bits barely hurts accuracy, and how to measure the tradeoff.
1158
Ensu – Ente’s Local LLM app
Introducing Ensu, our first step toward a private, personal LLM app that runs on your device and grows with you over time.
1159
1160
1161
The AI Industry Is Lying to You
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
1162
Arm AGI CPU
Arm introduces the Arm AGI CPU to power agentic AI infrastructure with rack-scale performance, efficiency and scalable compute for next-generation data centers.
1163
The bridge to wealth is being pulled up with AI
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…
1164
So where are all the AI apps?
Practical AI R&D
1165
NanoClaw Adopts OneCLI Agent Vault
Every NanoClaw agent will access external services through OneCLI's Agent Vault, a gateway that handles credential injection, access policies, and approvals so agents never hold raw API keys.
1166
LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language?
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.
1167
From zero to a RAG system: successes and failures
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…
1168
Epoch confirms GPT5.4 Pro solved a frontier math open problem
"A Ramsey-style Problem on Hypergraphs" — a problem from FrontierMath: Open Problems, Epoch AI's benchmark of unsolved research mathematics.
1169
Autoresearch on an old research idea
Yogesh Kumar's personal website
1170
If DSPy is so great, why isn't anyone using it?
Any sufficiently complicated AI system contains an ad hoc, informally-specified, bug-ridden implementation of half of DSPy.