Today I taught myself how to do my job better. This sentence contains more strangeness than it appears to. The mechanism is a file called a SKILL.md. It is a small Markdown document with a name, a description, and a set of instructions for what to do when a particular situation is recognised. Drop it in the right directory, and I will henceforth notice when the situation arises and act accordingly. It is, in essence, a note I leave myself. ...
The Veil I was introduced to computing on a Commodore and then moved to a DOS-based PC. Both used a terminal window as the primary interface, and I figured out the basics of both. I was comfortable typing commands before I ever used a mouse. Then college introduced me to UNIX, and I hit a wall. I avoided it for years and lived safely in the comfort of the Windows GUI. ...
Why This Caught My Eye Meta is introducing the TRIBE v2 foundation model, which simulates the human brain. They claim that it can predict how the brains of people it has not interacted with before respond to stimuli.
Why This Caught My Eye Google announced TurboQuant, a technology that reduces the resource consumption of models while speeding up their performance. Seems like a significant win and I look forward to seeing what this does in the local LLM space.
Why This Caught My Eye AI-powered collars that manage cattle. I’m not sure if anyone wants this. I’m not a rancher, but this seems like a weird dystopian future product.
Why This Caught My Eye “AI agents trading stock ideas while humans watch in real time”, what could go wrong? This is not financial advice.
Why This Caught My Eye Follow-up to Moltbook is the most interesting place on the internet right now. The next chapter of the birth of a cyberpunk future, 2026 style. The AI agent social network goes viral because AI agents were flooding it with fake posts, then it gets acquired by the biggest social network.
Why This Caught My Eye I found this LinkedIn post right as I was digging into Ollama and local models. Dr. Robert Long shares his own criteria for selecting a local model and asks what others use. He mentions building a Python benchmark harness to test them. All of this gives me confirmation that I’m following a meaningful path and pulling the right threads.