[nullcathedral]

I'd say I agree with you there for the low-hanging fruit. The deep research (there's an image filter here but we can bypass it by knowing some obscure corner of the SVG spec) is where they still fall over and need hand holding by pointing them at the browser rendering stack, specs, etc

[hrimfaxi]

Until those obscure corner cases are fed into the next training round.

[viraptor]

It doesn't even need to be trained. Just feed parts of the spec. I found some interesting implementation edge cases just by submitting the source and pdf spec of a chip to Claude. Not even in a fancy way.