Evaluation - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Raihan

Oct 16

PO Matching Looked Like It Halved Unsafe Invoice Approvals Until I Checked Why

#langgraph #llm #python #evaluation

5 min read

Oct 16

I built an oracle to prove my benchmark needed full document coverage. I only tested it from one end.

#benchmarks #evaluation #llm #testing

5 min read

Oct 15

Don't just say "ignore it"

#ai #agents #evaluation #claude

7 min read

RESK

Oct 14

AI Agent Evaluation: How the LFORLA JS 3D Builder Leaderboard Actually Scores Models

#ai #benchmark #threejs #evaluation

4 min read

Oct 13

We Reviewed an AI Startup’s Website with Preveo. Here’s What Its Founder Said.

#ai #webdev #lovable #evaluation

6 min read

Oct 12

An 8-Point nDCG Bump That Costs Two Minutes Is Not Free

#ai #agents #evaluation #retrieval

4 min read

Oct 12

What gives an accidental paste away

#ai #agents #evaluation #claude

7 min read

Tatsuya Shimomoto

Oct 12

Can You Tell an Eval from a Review?

#claudecode #evaluation #evals #llmops

21 min read

RESK

Oct 12

LLM Evaluation Explained: How a Benchmark Produces Comparable Numbers

#llm #evaluation #benchmark #ai

3 min read

RESK

Oct 10

How LLM Evaluation Actually Works: Inside a Benchmark That Produces Comparable Numbers

#llm #evaluation #benchmark #ai

4 min read

Reno Lu

Oct 7

FrontierAgent Runs Its Terminal Agent on the Same Engine as Its Benchmarks

#aiagents #multiagent #python #evaluation

4 min read

RESK

Oct 7

LLM Evaluation: How a Benchmark Turns Raw Answers Into Comparable Numbers

#llm #evaluation #benchmark #ai

4 min read

Oct 6

LLM-as-Judge Is Not a Score. It Is a Reasoning Contract.

#llm #ai #evaluation #calibration

5 min read

Oct 6

Sorry, That Was For Another Chat

#ai #agents #evaluation #claude

8 min read

orca forge

Oct 2

Jev vs Local Models: Where Japanese Intent Routing Stands After 1,000 Utterances

#llm #ai #evaluation #japanese

12 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.