DEV Community

#evals

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Loop drift: how agents convince themselves they're making progress
loopandretry profile

Loop drift: how agents convince themselves they're making progress

#failuremodes #evals #postmortem #loops
Comments
7 min read
One pass of my eval bills $9.14 on the API and $0 through the CLI
dylanmerigaud profile

One pass of my eval bills $9.14 on the API and $0 through the CLI

#ai #evals #claude #tooling
Comments
2 min read
Your LLM-as-judge is lying to you
loopandretry profile

Your LLM-as-judge is lying to you

#evals #llmasjudge #testing #bias
Comments
8 min read
Evaluating your evals: how to know the LLM judge is right
loopandretry profile

Evaluating your evals: how to know the LLM judge is right

#evals #llmasjudge #testing #metrics
Comments
5 min read
AI per developer: cosa accelera davvero (e cosa ti fa perdere tempo)
frontendfacile profile

AI per developer: cosa accelera davvero (e cosa ti fa perdere tempo)

#workflowaicoding #agentillm #evals #reliabilitytesting
Comments
4 min read
I have been Vibecoding Evals (works better than I thought)
juampitech profile

I have been Vibecoding Evals (works better than I thought)

#ai #llm #python #evals
Comments
3 min read
You Can't Unit-Test an LLM. Here's What I Built Instead.
amirmarcel profile

You Can't Unit-Test an LLM. Here's What I Built Instead.

#ai #python #llm #evals
Comments 5
8 min read
Rewriting prose until the tests pass: everything passed, but the check that mattered never ran once
matsumotory profile

Rewriting prose until the tests pass: everything passed, but the check that mattered never ran once

#testing #aiwriting #evals #promptengineering
Comments
6 min read
Rewriting research prose until the tests pass
matsumotory profile

Rewriting research prose until the tests pass

#testing #research #aiwriting #evals
Comments
5 min read
The 12-Prompt Eval I Run Before I Trust Any Model Upgrade
agnelnieves profile

The 12-Prompt Eval I Run Before I Trust Any Model Upgrade

#prompting #evals #modelmigration #claude
Comments
3 min read
How to Build AI Evals for Tool-Calling Agents
dhanushreddy29 profile

How to Build AI Evals for Tool-Calling Agents

#ai #evals #aievals #agents
1
Comments 2
17 min read
Do not choose an AI model from a leaderboard alone
edward_li_71f26791eac62b8 profile

Do not choose an AI model from a leaderboard alone

#ai #api #llm #evals
Comments
3 min read
# A 94% pass rate hid a PII leak in 6 test cases
ethanwritesai profile

# A 94% pass rate hid a PII leak in 6 test cases

#ai #llm #evals
Comments
5 min read
Zero Is Not a Score
nabbilkhan profile

Zero Is Not a Score

#advertising #aiagentoperations #developertooling #evals
Comments
4 min read
Not Enough SMEs or Customers to Make Your Evals? Make Some!
ohkpond profile

Not Enough SMEs or Customers to Make Your Evals? Make Some!

#ai #evals #testing #personas
1
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.