News for hackers. Stuff that matters.

A comment on The efficient frontier of LLM inference.

Re:The efficient frontier of LLM inference by fsckboy on Wednesday September 02, 2026 @12:30AM (#49531734)
"the efficient frontier" is an important landmark of (investment) portfolio theory. It proves/explains/illustrates how you can combine selections from a diffuse cloud of individual investments and still land on a frontier that is better than any of your individual choices. It's the entire basis of "diversify your portfolio".

The efficient frontier of LLM inference is a line, not a frontier.

this is a frontier:

https://upload.wikimedia.org/wikipedia/commons/e/e1/Markowit...

no matter how good is something a smart person writes down, a pleb will come along and try to hang on its coattails.

If you want to steal an idea for this, steal indifference curves, they'd make more sense.

[ Parent | on HN ]
Re:The efficient frontier of LLM inference by iciac on Wednesday September 02, 2026 @04:28AM (#49533425)
The authors are referring to a Pareto Frontier https://en.wikipedia.org/wiki/Pareto_front
[ Parent | on HN ]
Re:The efficient frontier of LLM inference by regularfry on Wednesday September 02, 2026 @06:24AM (#49534308)
> The efficient frontier of LLM inference is a line, not a frontier.

The efficient frontier of portfolio theory is also a line. Not sure I get your point here.

[ Parent | on HN ]
Re:The efficient frontier of LLM inference by fsckboy on Wednesday September 02, 2026 @03:13PM (#49540993)
not sure i get why you don't get it. why have the word frontier if it doesn't mean something different than other words?
[ Parent | on HN ]
Re:The efficient frontier of LLM inference by regularfry on Thursday September 03, 2026 @05:38PM (#49557450)
Because... it's an accurate description of the concept it's being applied to?
[ Parent | on HN ]