Alicloud.my.id

IT, Techno, Auto, Bike, Money

Dotnet Programming

My Eval Suite Was Lying to Me: Auditing the Judge, Not Just the Agent

Byali

Oct 1, 2026 #DOTNET
Share

I need to admit something first. For about six weeks this summer, I ran an LLM-as-judge eval suite against an agent I maintain, watched…

Continue reading on Medium »

 

 I need to admit something first. For about six weeks this summer, I ran an LLM-as-judge eval suite against an agent I maintain, watched…Continue reading on Medium » Read More Dotnet on Medium 

#dotnet

By ali

Related Post

Dotnet Programming

7 Mistakes I Made Building My First ASP.NET Core API (Tested on .NET 10)

Oct 1, 2026 ali
Dotnet Programming

I Stopped Asking AI to Write Code. I Started Asking It to Prove the Code Was Correct.

Oct 1, 2026 ali
Dotnet Programming

Harness, Framework, or SDK: I Audited My Own Agent Stack Against a Real Source-Code Study

Oct 1, 2026 ali

Leave a Reply

You missed

IT

The One Linux Tool That Replaces Your PDF Reader With Just a Keyboard

October 1, 2026 ali
IT

A beginner’s tour of the commands, files and permissions that power most of the cloud.

October 1, 2026 ali
IT

️E.D.I.T.H. // The Mysterio Protocol

October 1, 2026 ali
IT

Understanding CWE-24: Path Traversal: ‘../filedir’

October 1, 2026 ali