Comment by Chance-Device
4 hours ago
Claude thinks the user is always wrong. This was at its peak with Opus 4.8 but is still present in Opus 5 and to a lesser degree Fable.
It’s extremely annoying. If the user asserts anything, Claude has to disagree with it. It has to tack on clarifications that aren’t really clarifications, they’re just statements aimed at making whatever the user has said seem more wrong.
It even disagrees with itself. Whenever Claude writes a message that takes a position on something, its final one or two paragraphs will try to dismantle its own argument.
This is beside the point of being contrarian, but it’s also just so long winded.
I find myself using ChatGPT more these days, despite the fact that I don’t want to. That unfortunately says a lot about where Claude’s personality has ended up.
> It even disagrees with itself. Whenever Claude writes a message that takes a position on something, its final one or two paragraphs will try to dismantle its own argument.
I have agents adversarially check each other. When I switched to Opus 4.8 they began arguing EXTENSIVELY with each other. My code began to fill with comments about these arguments. Reviews would fail because the argumentative comments would get stale.
My build system came crashing down with a tsunami of disagreeable text.