A technical evaluation of workflow-based automation tooling for building enterprise-grade agentic systems using LLMs. It's good. Read more ›
Build mini-agents with 90%+ accuracy, whether you're a solo developer or an enterprise team. Get started with $300 in free credits. Read more ›
Vietnam's transition to IPv6 is inevitable, and those who move too slowly risk being left behind in the country's digital future, Deputy Minister of Science and Technology Pham Duc Long said on June 18. Read more ›
You might say the system packs two kilapixels of compute Read more ›
Homogenization is the consolidation of methods across machine learning: strong leverage toward many tasks, but a single point of failure. I keep reading it as if it were about us, and about what these tools do to the human mind. Read more ›
The AI co-founder for solo founders. Doesn’t sleep, doesn’t eat, and just merged a PR. Plan, ship, and launch in one continuous loop. Read more ›
Jos Benschop is climbing a ladder to get to the top of his newest machine. It’s a bit of a schlep. The contraption is the size of a double-decker bus—more than 150 tons of gleaming precision-milled aluminum covered in thousands of snaking tubes, colored cables, and pressurized tanks. From the ground, it looks like a… Read more ›
A Sherlock Holmes board game as an LLM-agent eval Read more ›
Back in 2022 and 2023 there were two big branches of machine learning happening at Meta1. The LLM work that led to Llama was a clean, smooth stack of repeated Transformer modules; the recommendatio… Read more ›
Add a streaming AI chat to any website, in minutes. Themeable, pluggable, zero framework dependencies. Read more ›
There’s a new paper out called “PivCo-Huffman” (HTML version with annotations here) and it’s very interesting. Normal Huffman decoding (and, to a lesser extent, encoding) is inherently quite serial. We can get explicit parallelism by using multiple streams, which scales just fine to moderate numbers of streams – something like 4-8 is usually not an […] Read more ›
OpenAI-compatible AI inference gateway. One key, every model. Read more ›
LeetCode for Machine Learning. Practice ML coding problems with a real Python execution environment. Read more ›
The only guaranteed way to preserve your digital privacy requires no special tooling. This post explains why, and offers practical methods to minimize internet exposure. Read more ›
The loop takes agentic AI a step further, by authorizing a swarm of agents to work continuously in the background, endlessly. Read more ›
A couple of weeks ago I saw a guy in the office with six instances of claude code, each in a different window. Read more ›
x86's lock-in is real. It's just furthest from the GPU. Read more ›
From pretraining to RLHF/GRPO — every algorithm hand-written in pure PyTorch. Read more ›
We are being sold LLMs as incredible productivity tools, and the more I hear that pitch the more I think about Michael Polanyi. He had a simple line: we know more than we can tell. He called the gap tacit knowledge. It is the stuff we pick up from experience and internalize without noticing, so we can't really explain it. How to ride a bike. When a deal feels off. Which of two correct looking designs is the one that quietly rots in six months. Read more ›