Opus 4.7 has been a real downgrade for me. I’m back to mid 2025 when I had to catch all the completely intermediary goals/assumptions the model is creating for itself

it's sort of good at thinking, writing specs, etc.. Also debugging. But as a coder: I see no advantage to opus 4.6 and I preferred sonnet most times already over opus 4.6.

You can still use older versions of Opus if they work better for you. Just need to set the environment variable.

I felt that but find it worked way better by invoking it with `claude --effort max` only

Yup I run Max only now. It's closer to the "old" Claude but still nerfed in my opinion.

My "mental scratchpad" needs to be as sharp as possible to maximize my intelligence. I think of the LLM as a scratchpad for my thinking, I hope the Anthropic team can see this.