Notes from the engine room.

Did this model learn a game? An attempt from the workshop: optimising models without training them.

We use open models and do not know what they were trained on. So we started looking inside: a second model examines the first and searches for traces, for example whether it was trained on a game, and which one. This is an attempt, not a result. But the research on it is surprisingly far along, and the reason we do it is tangible: if you know what is already inside a model, you can use it better at query time. Without a single training run.