It is unbelievable but true that there are multiple opportunities in any software to reduce the time it takes to run by a factor of 100
It is even more unbelievable but even more true that most engineering managers cannot understand the value of these gains
Replying to @flyingsaceur@ioc.exchange
@flyingsaceur agreed. I'm the author of a latency instrum lib for Golang, and a WIP book on perf optimization. sooooo many opportunties to reimplement designs/code to run faster or use less host resources. all about the trade-offs we choose to make, it seems. and younger folks spoiled by gadgets that would have been considered SOTA supercomputers just 20-40 years ago
Replying to @synlogic4242@vivaldi.net
@synlogic4242 you’re doing the lord’s work (the lord being the big O)
whether it’s throwing more tokens or more cloud spend or more bodies at a problem, people will do anything except revisit their assumptions