← Back to context

Comment by gs17

20 hours ago

> I really do not want to have to drop everything and verify that 10 behaves close enough to 9.9 for my specific task

Or worse, you run the evals and 10 is a huge regression from 9.9, and you get stuck with either a project to figure out if you can fix it or knowing the product will drop in quality in a way that's entirely outside your control.