1+ day, 13+ hour ago   (575+ words) By Nokka | September 11, 2026 People install Ollama and hit the same wall: responses are slower than expected even on good hardware. Most of the time the hardware is not the problem. The defaults are simply not tuned for sustained heavy use…...

6+ day, 8+ hour ago   (267+ words) 1. The Task and Asset State Stores With the Task State Store Airflow 3.3 utilizes tasks to save pieces of metadata that persist across retries. Instead of starting over from scratch, a subsequent attempt of the same task can fetch the metadata,…...

6+ day, 15+ hour ago   (709+ words) What does an AI coding agent need in order to be useful in a real software project? Not a toy... Tagged with ai, agents, softwareengineering, devtools....

1+ week, 3+ hour ago   (709+ words) When you run a 3-billion-parameter model like Llama 3.2 locally on commodity hardware, the initial experience feels like magic: it is fast, private, and runs completely offline with zero API costs. Then you put it in front of real operational data…...

1+ week, 4+ hour ago   (651+ words) If your Ollama install started timing out right after an upgrade, you're probably staring at this after five patient minutes: Nothing in that error says why. The model never finished loading. It's a regression that showed up in 0.32.10 and is…...

1+ week, 1+ day ago   (762+ words) I never built:31b. I built:31b-cloud. I asked for:31b-cloud. Ollama went looking for something else, didn't find it, and told me so, using a name that existed nowhere on my machine, in my registry, or in my head. TL;…...

1+ week, 3+ day ago   (1514+ words) Simon Willison calls it the lethal trifecta: private data, untrusted content, and a way to exfiltrate, all in the same session. A coding agent on your laptop has all three by default. It reads your code (private data), it reads…...

1+ week, 4+ day ago   (1723+ words) Airflow 3.3.0 shipped on 6 July 2026, with 3.3.1 following about five weeks later. It's a much smaller release than 3.0 was, and that's fine. Nothing about how you write Dags has changed. What did change is a set of things most of us have…...

1+ week, 5+ day ago   (1199+ words) A few years ago, I started thinking about a simple question: How far can we actually push an LLM on a complex software project? That's already well established. I mean something harder: Can an LLM take a complex problem, break…...

1+ week, 5+ day ago   (786+ words) By the end of this walkthrough, every DAG run in your Airflow instance emits structured lineage events that name the exact tables each task read and wrote, and you can open a graph and answer "which upstream job produced this…...