> The amount you can review before burning out is now the reasonable limit

I realized this is the crux of our moment, because a variant of Amdahl's law applies to AI code gen.

{time gained} = {time saved via gen AI} - {time spent in human review}

There's no way that results in a positive number with 100% human review coverage, which means that human review coverage is headed to < 100% (ideally as low as possible).

I'm not sure that's as certain, I think just by virtue or LLMs being better copypasting/integrated stackoverflow you can get a speed boost (prompts like "generate a similar test to this one checking condition X").

The question is whether humans can sensibly judge the break even point and not generate faster than that. It's very easy to get lost in the woods and suddenly have a bunch of generated stuff you no longer grok.