Changelog Update
- Significantly reduced “lazy” coding from GPT-4 Turbo due to new unified diff edit format
- Score improves from 20% to 61% on new “laziness benchmark”.
- Aider now uses unified diffs by default for
gpt-4-1106-preview.
- New
--4-turbocommand line switch as a shortcut for--model gpt-4-1106-preview.