Re:A Family Tree of Software Job Titles
by sverhagen on Sunday November 15, 2026 @07:15PM
(#50512394)
Just talking about software engineering, I think that the places where requirements are strong enough to be implemented unambiguously, are few and far between. So, it's "clearly possible", but rare, in my universe, your mileage may vary.
[ Parent
| on HN ]
Re:A Family Tree of Software Job Titles
by fc417fc802 on Sunday November 15, 2026 @07:22PM
(#50512446)
And yet somehow people are successfully leaving some projects almost entirely up to agents. Does that not run directly counter to what you're saying?
Also I will observe that something being rare is not in and of itself an indicator of whether or not it is reasonable. Many things are done a certain way because that's the conventional approach or it's more cost effective or due to some logistical concern.
In the case of software development it was previously cheaper not to exhaustively specify everything up front but I'd argue LLMs have upended that longstanding status quo within only the past year.
Re:A Family Tree of Software Job Titles
by sverhagen on Sunday November 15, 2026 @08:02PM
(#50512763)
I don't think that runs counter...
We had humans that were smarter than monkeys, dealing with imperfect requirements. Now we have LLMs that are smarter than monkeys, dealing with imperfect requirements.
LLMs don't work because of good requirements input, they work despite the poor requirements they're given.
Re:A Family Tree of Software Job Titles
by fc417fc802 on Sunday November 15, 2026 @08:56PM
(#50513102)
Okay but all you're arguing at that point is that it will continue to be rare because LLMs that exceed the capabilities of monkeys are readily available and not that much more expensive than their less capable cousins. Not that there's any inherent reason it's unrealistic to do so. With skyscrapers it's cheaper to make sure the specification is bulletproof and with software it's cheaper to kick it out the door while it still has more than a few holes in it.