1201
LLM Architecture Gallery
A gallery that collects architecture figures from The Big LLM Architecture Comparison and related articles, with fact sheets and links back to the original sections.
New
The latest blog posts to take off on Hacker News. 1,521 posts.
1202
A Visual Introduction to Machine Learning (2015)
What is machine learning? See how it works with our animated data visualization.
1203
The Appalling Stupidity of Spotify's AI DJ
Am I naïve in expecting Artificial Intelligence to be smart? Is my interpretation of the word “intelligence” too literal? And when an AI behaves stupidly, who’s to blame? The programmers or the AI entity itself? Is it even proper to make a distinction between the two? Or does the AI work in so mysterious a way that…
1204
Launching the Claude Partner Network
We’re launching the Claude Partner Network, a program for partner organizations helping enterprises adopt Claude.
1205
MCP is dead; long live MCP
Understanding the social media zeitgeist around CLIs and the premature death of MCP
1206
AI didn't simplify software engineering: It just made bad engineering easier
AI tools lower the barrier to producing code, not to building reliable systems. The hard part — maintaining alignment between specifications, tests, and implementation — has not gone away. Expertise still matters.
1207
1208
Claude Tips for 3D Work
Lessons learned from piloting in the third dimension
1209
Run NanoClaw in Docker Sandboxes
Every agent gets its own isolated container inside a micro VM. No dedicated hardware needed. No complex setup.
1210
Grief and the AI split
TL;DR: AI-assisted coding is revealing a split among developers that was always there but invisible when we all worked the same way. I've felt the grief too—but mine resolved differently than I expected, and I think that says something about what kind of developer I've been all along.
1211
Claude now creates interactive charts, diagrams and visualizations
Ask Claude to explain a concept or analyze your data, and it can respond with interactive charts, diagrams, and visualizations — rendered inline as part of the conversation.
1212
Document poisoning in RAG systems: How attackers corrupt AI's sources
RAG poisoning attack walkthrough: an attacker injects fabricated documents into a ChromaDB knowledge base and the LLM reports false financials as fact. Fully reproducible, 100% local, no GPU required.
1213
Are LLM merge rates not getting better?
I was reading the metr article on how llm code passes test much more often than it is of mergeable quality . They look at the performance of llm s doing programming when the success criterion is “passes all tests” and compare it to when the success criterion is “would get approved by the maintainer”. Unsurprisingly…
1214
Executing programs inside transformers with exponentially faster inference
We build a computer inside a transformer — executing arbitrary C programs for millions of steps with exponentially faster inference via 2D attention heads.
1215
Reliable Software in the LLM Era
Quint - Executable specs for reliable systems
1216
How much of HN is AI?
TL;DR: 62% as of September 2026. This is up from ~40% in February.
1217
Many SWE-bench-Passing PRs would not be merged
We find that roughly half of test-passing SWE-bench Verified PRs written by recent AI agents would not be merged into main by repo maintainers. A naive interpretation of benchmark scores may lead one to overestimate how useful agents are without more elicitation or human feedback.
1218
I'm glad the Anthropic fight is happening now
“Preface to the highest stakes negotiations in history.”
1219
How we hacked McKinsey's AI platform
An autonomous AI agent found a SQL injection in McKinsey's Lilli AI platform. What it extracted was worse than we expected.
1220
1221
TADA: Speech generation through text-acoustic synchronization
TADA (Text-Acoustic Dual Alignment) is Hume AI's open-source speech-language model that synchronizes text and audio one-to-one.
1222
Against vibes: When is a generative model useful
Let's suppose I wanted to answer a question: is the tool X useful for the task Y. If I were scientific about this, I would analyze the properties of tool X and develop a model, and the task Y and the requirements for it and develop a model, and I would us...
1223
1224
I built a programming language using Claude Code
Over the course of four weeks in January and February, I built a new programming language using Claude Code. I named it Cutlet after my cat. It’s completely legal to do that. You can find the source code on GitHub , along with build instructions and example programs .
1225
Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs
ML, Biotech, Hardware, and Coordination Problems. Sometimes I write about hard problems and how to solve them.
1226
Levels of Agentic Engineering
AI's coding ability is outpacing our ability to wield it effectively. That gap closes in levels — 8 of them. Here's the progression from tab complete to autonomous agent teams.
1227
Emacs and Vim in the Age of AI
It’s tough to make predictions, especially about the future. – Yogi Berra
1228
Learnings from paying artists royalties for AI-generated art
A retrospective on Tess.Design, our attempt to make an ethical, artist-friendly AI marketplace. We launched Tess in May 2024 and shut it down in January 2026.
1229
Open Weights isn't Open Training
How many monkey-patches does it take to post-train a trillion parameter model?
1230
No, it doesn't cost Anthropic $5k per Claude Code user
The viral claim that Anthropic loses $5,000 per Claude Code subscriber doesn't survive basic scrutiny. Let's do the actual maths.