Posted on Sat 29 August 2026 in AI
Retrieval-Augmented Generation — RAG — has quietly become the default way to make LLMs actually useful with real-world documents. You index a PDF, embed the chunks, retrieve the relevant ones at query time, and pass them to the model. It works. People ship it.
But there's …
Posted on Sat 04 July 2026 in AI Agents
They're eager, they're capable of a lot, and they will absolutely try to put the ketchup in the dishwasher if nobody's watching. It's not that they're malicious. It's that competence and judgment aren't the same thing.
AI agents — the systems …
Posted on Mon 29 June 2026 in AI Engineering
No re-explaining. No "as I mentioned before." Just an assistant that remembers what you told it last week and keeps building from there.
If you've wanted that, you've bumped into one of the hardest problems in …
Posted on Mon 29 June 2026 in AI Engineering
Not just any face — your face. In dim light. With glasses on. Three years after you set it up.
Behind that everyday magic sits a fascinating idea called ArcFace. Don't let the name fool …
Posted on Mon 29 June 2026 in AI Agents
That's basically what it feels like to debug an AI agent system.
You watch it mess up. You check the logs. The logs cheerfully tell you what happened — it called a tool, it got a …