Sure they care about elegance, or at least brevity. Minimizing tokens out, or generally "token efficiency," is part of the objective function for these systems. It doesn't mean they are perfect at it though.

▲

windexh8er 3 hours ago | parent | next [-]

"They" don't "care" about anything. It is a stateless computational run across thousands of semiconductors. There is no objective this software has other than the computational function completing. To care would mean the model would have a level of discernment that goes along with sentience.

	▲	js8 2 hours ago \| parent [-]
		You are kind of ignoring the Dennett's idea of different stances: https://en.wikipedia.org/wiki/Intentional_stance You're looking at humans from intentional stance, but at LLMs from design stance, which would be a form of categorical error.

▲

Someone 4 hours ago | parent | prev | next [-]

> Minimizing tokens out, or generally "token efficiency," is part of the objective function for these systems.

First time I heard that, and I doubt it. Don’t customers pay for output tokens? If so, why would a company specifically spend time training their LLM to generate fewer?

	▲	yreg 4 hours ago \| parent [-]
		So they can charge more per token and decrease the pressure on their infra.

▲

senorrib 4 hours ago | parent | prev [-]

You clearly haven't used Claude to generate code or documentation.

▲

nelox 4 hours ago | parent [-]

"First rule in government spending: why build one when you can have two at twice the price" - S.R. Hadden

	▲	KPGv2 4 hours ago \| parent [-]
		Personally, I've found city roads to be more reliable than the private roads where I live.