Me Dealing with AI Training Bias
This started for me in 2024, when Bulma v1 came out. I went looking for a React package that supported it. There wasn't one yet.
This started for me in 2024, when Bulma v1 came out. I went looking for a React package that supported it. There wasn't one yet.
Ask a coding agent for a dashboard in a library its training data barely saw, and one of two things happens: it quietly switches to the popular library it has seen a million times, or it stays loyal and invents props that don't exist. We fought that with agent skills, playbooks that teach an agent our library. This is the story of what came after: proving the skills actually work, then making them better the way evolution would, just faster.
A coding agent can't one-shot a library its training data barely saw. Ask one for a dashboard in an under-represented library and you get one of two failures: it quietly reaches for the incumbent it has seen a million times, or it stays loyal and invents props that don't exist. bestax's answer is to make the real, current API machine-legible so one shot is enough, and this post is everything that ships today.