On: GPT-5.6

[coldtea]

"Their performance depends solely on the model training before release and how well you curate the context you feed it".

Wrong. The face-saving backtracking doesn't change that.

[daveguy → coldtea]

The models do not get better until a new one is released. And we are already at diminishing returns. So sorry. Also sorry you don't know the difference between a model and a context, harness, router, or cache.