I was asked to evaluate the last version of Gemini for work. I set up the agent, gave it a robust gemini.md file, and asked it about a bug I was seeing. It told be the bug was because I had spelled “Arrange” with 3 Rs. Except:
I hadn’t
Doing so would not have caused the bug I was seeing
3 consecutive letter R’s didn’t exist anywhere in the code base
I once got an Agentic AI stuck in a loop where it kept proposing unrelated code to fix an issue. It would add it, break, then detect it was unrelated, delete it, retry and see the issue was still there. So it would add the code back and redo the loop.
I was asked to evaluate the last version of Gemini for work. I set up the agent, gave it a robust
gemini.mdfile, and asked it about a bug I was seeing. It told be the bug was because I had spelled “Arrange” with 3 Rs. Except:Gemini 3 really had no where to go but up.
I once got an Agentic AI stuck in a loop where it kept proposing unrelated code to fix an issue. It would add it, break, then detect it was unrelated, delete it, retry and see the issue was still there. So it would add the code back and redo the loop.
Clearly we are on the path to replacing humans.