Posts

LLMs Don’t Actually “Call” Tools Here is a fact that surprises most people: LLMs cannot run code. They cannot call APIs. They cannot read files. All they do is predict the next token — they output raw text, one piece at a time. So how do they “use tools”? The trick: structured wishes During training, models are fine-tuned on augmented datasets that include tool call examples. The training pipeline works roughly like this: ...

So I made a blog. Nothing grand — just a small burrow where I stash things I pick up along the way. I spend most of my time building software and poking at AI. Every now and then I stumble on something shiny — a neat trick, a useful pattern, an idea that clicks. This is where those things end up, mostly so I don’t forget them. If you happen to wander in and find something useful, great. If not, that’s fine too. The squirrel hoards for itself first. ...