I’ll back you up on this. I’ve had the experience of seeing Claude fabricate stuff, and then when I challenge it, it says something like “I guessed, let me look deeper” and then it indeed does check deeper with docs or a configured LSP etc and then discovers the real answer.
It doesn’t matter if this was the result of reasoning or just more pattern prediction, the result is that if you tell it not to guess, it responds appropriately.
I’ll back you up on this. I’ve had the experience of seeing Claude fabricate stuff, and then when I challenge it, it says something like “I guessed, let me look deeper” and then it indeed does check deeper with docs or a configured LSP etc and then discovers the real answer.
It doesn’t matter if this was the result of reasoning or just more pattern prediction, the result is that if you tell it not to guess, it responds appropriately.