Is Fable really that much different? I almost instinctively create elaborate processes, workflows, set up a bunch of linters and dump research docs any time I bootstrap a new project regardless of what model I'm using. They all spiral out of control if they're not following a predefined process.

(Based purely on my feels of using both daily since forever)

Claudes are more creative and get shit done, suggesting and implementing stuff you didn’t ask for but actually kinda needed. Will leave gaps and bugs though. More of an artist, communicates a bunch during the dev process too.

GPT is the engineer, given exact specs it’ll disappear into its dark corner and putter away at doing exactly what was asked, nothing more nothing less. Very very good at spotting gaps from Claude’s get shit done code.

There's been a ton of discussion on HN about this but yes. It's a totally different level from Opus.