Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
Tiny model. Big decisions. Series' Articles
Back to PerryLink's Series
Tiny model. Big decisions. — How I built a 144.3M-parameter typed decision model that routes 55.0% of agent decisions off LLMs
PerryLink
PerryLink
PerryLink
Follow
Oct 8
Tiny model. Big decisions. — How I built a 144.3M-parameter typed decision model that routes 55.0% of agent decisions off LLMs
#
showdev
#
ai
#
llm
#
opensource
1
reaction
Comments
2
comments
4 min read
Moderation
0/31 vs 30/31: the question is the gate — wiring a local decision layer into my agent
PerryLink
PerryLink
PerryLink
Follow
Oct 12
0/31 vs 30/31: the question is the gate — wiring a local decision layer into my agent
#
ai
#
llm
#
agents
#
devtools
Comments
1
comment
7 min read
Moderation
We measured our plugin's "token savings". At τ=0.6, it was 8.5%.
PerryLink
PerryLink
PerryLink
Follow
Oct 13
We measured our plugin's "token savings". At τ=0.6, it was 8.5%.
#
ai
#
llm
#
performance
#
machinelearning
2
reactions
Comments
2
comments
6 min read
Moderation
Local 144.3M or a hosted API for your approval gate? Three questions and one honest table.
PerryLink
PerryLink
PerryLink
Follow
Oct 13
Local 144.3M or a hosted API for your approval gate? Three questions and one honest table.
#
ai
#
llm
#
machinelearning
#
localai
Comments
Add Comment
6 min read
Moderation
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account