alt Hacker NewsI get this a lot too, have made most of the Gemini models essentially unusable for agent-esque tasks. I tested with 2.5 pro and it still sometimes devolved into random gibberish pretty frequently.
I get this a lot too, have made most of the Gemini models essentially unusable for agent-esque tasks. I tested with 2.5 pro and it still sometimes devolved into random gibberish pretty frequently.