alt Hacker NewsThat's quite common with many models, after "High" reasoning, over-thinking starts occurring and the model skips over the right solution by convincing itself otherwise.
That's quite common with many models, after "High" reasoning, over-thinking starts occurring and the model skips over the right solution by convincing itself otherwise.
> That's quite common with many models
Such as?
I can't think of any. Diminishing returns, yes. Occasionally flat, yes. Downright regression, no.