We can still run an LLM scorer but I like the simplicity of keeping the tooling something we can uniquely do. It also lines up with things we need to do anyway.

I’m always looking for these “double entendre” solutions - meaning one solution that solves a few problems (even partially) for us.

k00b

How did you ultimately decide not to move forward with the idea?

I was kinda interested in seeing some metrics about it, like the accuracy rate you could get on identifying slop/spam.

AskSN

devs

Best small and open instruct models?

How did you ultimately decide not to move forward with the idea?  

I was kinda interested in seeing some metrics about it, like the accuracy rate you could get on identifying slop/spam.