Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
The road measurement took me down Series' Articles
Back to LYR's Series
One setting took output tokens to 1/27, latency to 1/4, and cost to 1/5
LYR
LYR
LYR
Follow
Aug 3
One setting took output tokens to 1/27, latency to 1/4, and cost to 1/5
#
performance
#
llm
#
testing
#
ai
Comments
Add Comment
6 min read
Last year's right answer becomes this year's wrong one
LYR
LYR
LYR
Follow
Aug 3
Last year's right answer becomes this year's wrong one
#
performance
#
devops
#
testing
#
ai
Comments
Add Comment
6 min read
Some AI models are disqualified before you ever measure quality
LYR
LYR
LYR
Follow
Aug 3
Some AI models are disqualified before you ever measure quality
#
machinelearning
#
performance
#
llm
#
ai
Comments
Add Comment
6 min read
Borrowed AI disappears overnight
LYR
LYR
LYR
Follow
Aug 3
Borrowed AI disappears overnight
#
devops
#
machinelearning
#
startup
#
ai
Comments
Add Comment
6 min read
I brought AI in-house: E2E ~500ms 120ms, cost down to 1/3–1/10
LYR
LYR
LYR
Follow
Aug 3
I brought AI in-house: E2E ~500ms 120ms, cost down to 1/3–1/10
#
devops
#
performance
#
machinelearning
#
ai
Comments
Add Comment
10 min read
You are the bottleneck
LYR
LYR
LYR
Follow
Aug 3
You are the bottleneck
#
testing
#
architecture
#
llm
#
ai
Comments
Add Comment
6 min read
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account
