Gemini 4 Argon has proven to be outright unusable for real code work in my codebases. It aggressively hallucinates about how systems work.

This isn't the usual "oh it's 5% worse in this way, 3% better in others".

In almost every test I ran, Gemini was factually wrong about over 50% of it's claims.

This model is a straight up liability. Keep it away from your code.

I go way more in depth on the methodology here in my video

x.com/theo/status/21…