Comment by squidbeak

This sounds like all engineering, rather than just AI. The greatest effort given to the last small difficult details, often for results that seem trifling but which matter at scale.

But it's a poor argument. The code improvements with these things is hardly marginal - Opus 4 was only 16 months ago. How many of the grumblers would want to ditch their modern stalwarts and return to it? What is marginal is the nitpicking - and like anything in tighter bounds, it's more intense with a narrower scope.

These threads always have many dissatisfied voices with repeating complaints - about overwrought thinking and disappointing output - alongside others who are amazed at the sudden real extra capabilities. Both are true at once - capabilities are rapidly increasing, but nowhere near ideal, which is why this attempt to tag it as Neijuan, though interesting, is ultimately a load of bollocks.