It does well with screenshot-calculus for me. For example, I pasted a screenshot of the Layer Norm equation into Claude Code 2 and asked:

"Differentiate y(x) w.r.t x, gamma and beta."

It not only produced the correct result, but it understood the context - I didn't tell it the context was layer norm, back-propagation and matrices.

This release is a step function for my use cases.

My screenshot came from here: https://docs.pytorch.org/docs/stable/generated/torch.nn.Laye...