I just caused an automated system which is dumb to apologize-in-advance to an automated system which is smart. (~ "The system which generates this file can't do string manipulation. You can, though, so to succeed you will want to... Sorry about extra work.")
Programming in 2026.
Users dismissed the idea of one AI being smarter than another after a developer tricked a 'dumb' system into apologizing, calling the smarter one dangerously stupid and warning against loading nonsense into its context window.
No Digg Deeper questions have been answered for this story yet.
"Does that actually matter?"
I am positive one of the two systems can't possibly have an opinion and pretty sure the other one can't either but it just feels so aesthetically wasteful that at a minimum I want to apologize to future engineers who might read what I cooked up.
I just caused an automated system which is dumb to apologize-in-advance to an automated system which is smart. (~ "The system which generates this file can't do string manipulation. You can, though, so to succeed you will want to... Sorry about extra work.")
Programming in 2026.
"What kind of programmable automated system can't do string manipulation!?"
Handlebars templating, apparently. (I'm building an LLM-available index into some of my sites to have various tools able to read status of pieces w/o needing direct DB access.)
@patio11 i find myself being mindful of the fact that the LLM has some theory-of-mind about itself and about me.
something about this is very "westerner adapting to living in Asia".
on an unrelated note my wife hates when i compare her to LLMs.
@patio11 Neither has an opinion, and the one you think is smart is actually dangerously stupid. Don’t load nonsense into its context window.