DEV Community

Testing

Find those bugs before your users do! 🐛

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How to Test Non-Deterministic AI Agents (When temperature=0 Isn't Enough)

How to Test Non-Deterministic AI Agents (When temperature=0 Isn't Enough)

Comments
8 min read
Strip Location From Both Halves of an iOS Live Photo Before Upload

Strip Location From Both Halves of an iOS Live Photo Before Upload

Comments
2 min read
Ship a Restart-Safe Upload CLI That Survives an Expired Resume URL

Ship a Restart-Safe Upload CLI That Survives an Expired Resume URL

Comments
1 min read
วิธีทดสอบ AI Agent ที่ไม่เป็นเชิงกำหนด (เมื่อ temperature=0 ไม่เพียงพอ)

วิธีทดสอบ AI Agent ที่ไม่เป็นเชิงกำหนด (เมื่อ temperature=0 ไม่เพียงพอ)

Comments
3 min read
Test a Saga When Compensation Times Out and the Message Is Delivered Twice

Test a Saga When Compensation Times Out and the Message Is Delivered Twice

2
Comments
2 min read
Cómo Probar Agentes de IA No Deterministas (Cuando temperatura=0 No Basta)

Cómo Probar Agentes de IA No Deterministas (Cuando temperatura=0 No Basta)

Comments
8 min read
كيفية اختبار نماذج الذكاء الاصطناعي غير الحتمية: عندما لا تكفي درجة الحرارة = 0

كيفية اختبار نماذج الذكاء الاصطناعي غير الحتمية: عندما لا تكفي درجة الحرارة = 0

Comments
2 min read
Cara Menguji Agen AI Non-Deterministik (Saat temperature=0 Tidak Cukup)

Cara Menguji Agen AI Non-Deterministik (Saat temperature=0 Tidak Cukup)

Comments
7 min read
Cách kiểm thử agent AI không xác định (Khi nhiệt độ=0 là chưa đủ)

Cách kiểm thử agent AI không xác định (Khi nhiệt độ=0 là chưa đủ)

Comments
13 min read
Reject Image Polyglots After EXIF Removal, Before They Reach Your CDN

Reject Image Polyglots After EXIF Removal, Before They Reach Your CDN

Comments
2 min read
I Confirmed My API Formula at the One Point Where Both Formulas Agree

I Confirmed My API Formula at the One Point Where Both Formulas Agree

1
Comments
6 min read
Goodhart in Agent Pipelines: Five Cheap Ways to Pass

Goodhart in Agent Pipelines: Five Cheap Ways to Pass

Comments 2
8 min read
Your cheap LLM relay might be swapping the model. Here's how to catch it.

Your cheap LLM relay might be swapping the model. Here's how to catch it.

Comments
7 min read
Getting Started in QA

Getting Started in QA

Comments
1 min read
A benchmark is only as good as the model you use to grade it

Costs twenty-one cents and exposes grading bias

A benchmark is only as good as the model you use to grade it

2
Comments 5
9 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.