I can already tell you for sure that those comments are a liability time bomb as soon as enough codebase changes and if the ai forgot to update those comments now it's gonna contextualise or hallucinate logic that doesn't make sense. It's work should be measured on the correctness and maintainability of what it generated, comments as soon as they become stale that's a ticking bomb.
There's also an unresolved bug when a certain email is both coming from an on-prem exchange and at the same time is used as a registered account at Microsoft, outlook seems to have continuous disconnections and prompts to login into the Microsoft account in outlook rather than sticking to the already logged in exchange email. Frustrating to say the least.
That's true for new projects, I've found that as a bootstrap mechanism it is not ideal, takes away your hard earned preferences/know-how abs leaves you barely engaged on the technical path. On the other side I already have quite big codebases, some legacy and inherited, there exist vast amount of context to work on and figure out stuff/fixes/bugs/improvements and Claude Code excels 95% of the time in figuring the existing flows and functionality, if a vague or precise issue is known that's facing some files elaborations or user work flows it can do a good job in pointing out what are, with a high chance, the issues.
I arrived at this conclusion too after 3 years of smart working, it's unreasonable to have today an obliged/implicit sacrifice of time and money that's commuting to the work place.
I would have to disagree, so far the new file API has been the most buggy experience for many apps that have to use files every time that the app is running or is in background, and this is from a user experience perspective alone.
I can understand why the developers can't be bothered with a badly thought out new system.
