Kimmonismus posted that Claude Code appeared to run high reasoning effort at a lower level than before, making Fable feel dumber. Anthropic engineer Thariq replied that nothing changed on the models and the display was a numerical mapping issue with no performance regression. Kimmonismus added that Opus 5 repeatedly feels like a downgrade, producing sloppy mistakes and ignoring instructions. Thariq acknowledged the model is spiky and stated the team is working to make outputs consistent and warm while rolling out easier feedback tools.