alt Hacker NewsI have made an observation that others have not discussed, that the real gem of our collective LLM experience is the proper documentation of “skills.”
Am I the only one who has noticed that the proper documentation of skills we do for LLMs after so many decades of neglecting junior and mid level roles are the real work?
We carefully explain to our LLMs policies, procedures, and practices which for generations before we have vaguely arbitrarily and ambiguously expected each human role to “figure out” for themselves?
Simply as a catalog of expectations our experiences have been valuable, apart from the “automated” aspects the LLms provide.
One of the ways I think the effect of LLMs on productivity (in software, anyway) will be tempered is that the work required to use them effectively & safely is all work we were supposed to be doing, but largely were not, at least not as completely as we aspired to. Exactly what you mention, much more detailed and thought-through feature requests, more-complete and higher-quality test suites, large and high-quality test datasets, documentation, thorough code review, all that stuff, all of it falling well under what we "should" be doing at every place I've ever worked, in terms both of quality and amount of it that we did.
They won't accelerate software development to the degree naïve analysis might suggest without significantly harming quality and reliability unless we start doing all those things we've been neglecting much better, which adds more work... with the result that I think our diverging paths here are "much worse software, made faster" or "software at least as good, with better supporting artifacts, but barely, if at all, faster to develop"