I tried Fable 5.2 tonight, asking it for a code review of an in-browser machine vision project done by Opus 5.5 over the last 11 days. It used up my 5-hour token budget in half an hour and reported 7 serious bugs; if they're real, they're pretty bad. It's also suggesting that I take a different overall approach to parts of the problem.
But that's just a first impression.