Re:MAI Code 2 and Code 2 Flash
by stingraycharles on Tuesday November 17, 2026 @06:33PM
(#50539754)
Isn’t Copilot Code Review using OpenAI’s models? As in, if it’s currently not good enough, these two new models are unlikely to make any impact?
[ Parent
| on HN ]
Re:MAI Code 2 and Code 2 Flash
by LaurensBER on Wednesday November 18, 2026 @02:00AM
(#50542790)
We've found that the challenge with code review is that you have very limited ability to customise it.
We've replaced it with a bot that does the same thing, except we fully control it now. So we can route crucial parts of the codebase to SOTA models, tag security if needed, etc.
I would love to know more about this. Even with other SOTA models doing a "review". It won't find anything and then Copilot Review will find 3 other things. It seems weird that they swing from yep we fixed everything to completely missing two of the same columns in an SQL query.