logoalt Hacker News

Nevermark • today at 5:37 PM • 0 replies • view on HN

> I’m sorry but isn’t this just over fitting based on conversational adaption. But worse since it’s self conversation? Resulting in the exact same problem 4o1 had: sycophancy? But again worse.

To me this comes across as word salad.

The edits are done based on reasoning, to accomplish a "target" improvement, that is itself reasoned and designed, taking into account a reasoned understanding of the existing functionality of the weights.

This is the furthest thing possible from some gradient optimization "over fitting" weights to tune a pedantic measure/target. That could be relegated to one-time greenfield-model bootstrapping.