News for hackers. Stuff that matters.
Re:MAI Code 2 and Code 2 Flash by SillyUsername on Tuesday November 17, 2026 @10:16PM (#50541424)
Whatever happened to the Microsoft Phi series?

I felt that the training data and behaviours for this at the time were very OpenAI like, due to responses similar in structure to ChatGPT (like how ChatGPT now usually has a section at the end "Why this matters")

Re:MAI Code 2 and Code 2 Flash by nl on Wednesday November 18, 2026 @01:35AM (#50542620)
You are the first person anywhere on the internet that I've seen who rated Phi at all.

I think the general impression was that it was one of the most benchmaxxed models around (presumably not deliberately - probably because of all synthetic data they used).

I certainly found that as soon as you went slightly out of the distribution it was trained on (text book type data) it was terrible.