1321
PyTorch Internals: Ezyang's Blog
This post is a long form essay version of a talk about PyTorch internals, that I gave at the PyTorch NYC meetup on May 14, 2019.
New
The latest blog posts to take off on Hacker News. 3,091 posts.
1322
Block AI Scrapers with Anubis proof-of-work
I got tired with all the AI scrapers that were bullying my git server, so I made a tool to stop them for good.
1323
How I accepted myself into Canada's largest AI hackathon
i <3 firebase
1324
LLM Agents Are Simply Graph – Tutorial for Dummies
Ever wondered how AI agents actually work behind the scenes?
1325
AI Blindspots – Blindspots in LLMs I've noticed while AI coding
Blindspots in LLMs I’ve noticed while AI coding. Sonnet family emphasis. Maybe I will eventually suggest Cursor rules for these problems.
1326
Hacking Your Own AI Coding Assistant with Claude Pro and MCP
Reverse Engineering Reality
1327
The model is the product
Old data, new models
1328
How Cursor (AI IDE) Works
Turning LLMs into coding experts and how to take advantage of them.
1329
AI Is Making Developers Dumb
LLMs are making software engineers dumber.
1330
"Wait, not like that": Free and open access in the age of generative AI
The real threat isn’t AI using open knowledge — it’s AI companies killing the projects that make knowledge free
1331
1332
1333
People are just as bad as my LLMs
Last year I created a fun little experiment where I asked a bunch of LLMs to rank 97 hackernews users using their comment history based on whether they would be good candidates for the role of “software engineer at google”. (yes yes, seems silly I know, you can read part 1 and part 2 but […]
1334
Generative AI hype peaking?
I have been a skeptic of some of the more breathless claims made for Generative AI since at least October 2023, when I participated in a panel organized by S...
1335
With AI you need to think bigger
I have noticed something in the past 12 months, something a little profound. I have noticed that I am no longer scared that a project will be too big or too complex for me, or that a project will use a technology or programming language I don’t know.
1336
MCP vs. API Explained
Model Context Protocol (MCP) is an open standard that connects AI models to tools and data sources efficiently. This guide breaks down MCP’s architecture, benefits, and how it differs from traditional APIs
1337
The Einstein AI Model
I shared a controversial take the other day at an event and I decided to write it down in a longer format: I’m afraid AI won't give us a compressed 21st century.
1338
Long Read: Lessons from Building Semantic Search for GitHub and Why I Failed
Made in Notion, the connected workspace where AI agents and teams organize docs, projects and knowledge together.
1339
AMD YOLO
AMD is sending us the two MI300X boxes we asked for. They are in the mail.
1340
Why I find diffusion models interesting?
HN Discussion
1341
Automatically tagging politician when they use their phone on the livestreams
How does it work? Every meeting of the flemish government in Belgium is live streamed on a youtube channel. When a livestream starts the software is searching for phones and tries to identify a distracted politician. This is done with the help of AI and face recognition. The video of the distracted politician are then…
1342
Skynet won and destroyed humanity
For a very long time, it appeared obvious to outside observers of the time flow that Skynet would never win the war, and never annihilate humanity.
1343
Writing an LLM from scratch, part 8 – trainable self-attention
Moving on from a toy self-attention mechanism, it's time to find out how to build a real trainable one. Following Sebastian Raschka's book 'Build a Large Language Model (from Scratch)'. Part 8/??
1344
ARC-AGI without pretraining
We solve 20% of ARC-AGI-1 with no pretraining by minimizing the description length during inference time, with the only data involved being the target puzzle itself.
1345
1346
DeepSeek's smallpond: Bringing Distributed Computing to DuckDB
DeepSeek is pushing DuckDB beyond its single-node roots with smallpond, a new, simple approach to distributed compute. But does it solve the scalability challenge—or introduce new trade-offs?
1347
The Differences Between Deep Research, Deep Research, and Deep Research
Dive into the world of AI engineering with this exploration of Deep Research in report generation. Learn how LLM-as-a-judge systems, machine learning, and ev...
1348
Hallucinations in code are the least dangerous form of LLM mistakes
A surprisingly common complaint I see from developers who have tried using LLMs for code is that they encountered a hallucination—usually the LLM inventing a method or even a full …
1349
GPT-4.5: "Not a frontier model"?
OpenAI's latest model raises more questions than answers, but no, the AI bubble isn't popping quite yet.
1350
Making o1, o3, and Sonnet 3.7 hallucinate for everyone
My (ops-but-sometimes-writes-scripts-to-help-out) coworker just tapped on my shoulder and asked me to look at his code that wasn't working. It was a bit something like this: