I thought you were setting 'agent loops' that run autonomously without looking at the code ever.
So, how do you know that it's "the best model for coding" and how it was measured?
Fable 5 is now available in Claude Code and Cowork
Fable is the best model I have used for coding, by a wide margin. It is a big step up, enabling less prompts and steers, more efficient token use, better code quality, better tool use, more intelligent self-verification, longer running sessions, and higher trust & autonomy.
Happy coding!
@bcherny > Fable is the best model I have used for coding, by a wide margin
How do you know that if the only thing you do is “run agent loops” without looking at the code?
I already have so many AI skills for different situations that I’ve started forgetting what I actually have. I need to build some kind of skill manager
On Motorola devices, even on flagship ones costing almost 2k$, a system app intercepts the opening of the Amazon app for some reason only from the app drawer, not from the home screen, and swaps in a URL with a referral link, and the link even leads to a fashion blog website. Lmao, wtf
https://t.co/aPnUWSKtTK