News for hackers. Stuff that matters.
Re:"I can tell you wrote this yourself" by MrScruff on Friday November 20, 2026 @04:11AM (#50572099)
AI behaves like a constraint solver. You put in the right set of constraints (on writing style, on technical details, on structure) and with a sufficiently capable model what will come out is a close approximation of something you might have produced, or at least something you might have been happy to receive from someone else. There will usually be aspects that aren’t quite right, so you add more constraints.

If you have a job/life where there are more things you want/need to achieve than you have time for, this can be a significant accelerant.

It does require the ability to judge when something is good enough of course.

This is actually no different to leading teams of humans. You guide individuals and set the standards and take responsibility for the output of the team.

Re:"I can tell you wrote this yourself" by ctenb on Friday November 20, 2026 @04:28AM (#50572243)
I would say that "solver" is the wrong framing, as it implies your problem is rigid and there is a space of correct solutions. Rather, it behaves like a probabilistic heuristic search algorithm.
Re:"I can tell you wrote this yourself" by fwlr on Friday November 20, 2026 @04:37AM (#50572312)
Most of the constraints you think apply to the task are actually shallow proxies for complex sets of properties that reliably arise when a socialized human from a similar culture attempts to solve for the constraint. As such, that sense of “aspects that aren’t quite right” will be inordinately hard to eliminate by adding more shallow proxy constraints. However, because an unbounded number of shallow-proxy-constraints have Greenspun’s tenth nature for sets of properties, it will never be impossible.