DEV Community

Testing

Find those bugs before your users do! 🐛

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
My LLM Critic Flip-Flops on Every Run. That's Fine — Because a Frozenset Decides What's Fatal.

My LLM Critic Flip-Flops on Every Run. That's Fine — Because a Frozenset Decides What's Fatal.

10
Comments 1
7 min read
True Randomness in Laravel with Lararand

True Randomness in Laravel with Lararand

3
Comments
4 min read
OpenAI Usage API api_key_id: Reconcile Tokens and Costs by Key

OpenAI Usage API api_key_id: Reconcile Tokens and Costs by Key

5
Comments
4 min read
The Gate That Stayed Silent — When a Blocker Count That Drops Reads as Improvement

The Gate That Stayed Silent — When a Blocker Count That Drops Reads as Improvement

10
Comments 2
5 min read
Your agent demo is rigged (mine was too), so I let the judges write the tests

Your agent demo is rigged (mine was too), so I let the judges write the tests

Comments
4 min read
Fifty Green Tests, Two Real Bugs, and the Oracle One `npm install` Away

Fifty Green Tests, Two Real Bugs, and the Oracle One `npm install` Away

Comments
9 min read
An AWS Labs agent-eval sample uses the same model as judge and subject

An AWS Labs agent-eval sample uses the same model as judge and subject

Comments
3 min read
Is an AI Product Still the Same After Its AI Layer Changes?

Is an AI Product Still the Same After Its AI Layer Changes?

Comments
1 min read
I Built GoleTalk — A Somali-First Social Platform Built for the Somali Internet 🇸🇴

I Built GoleTalk — A Somali-First Social Platform Built for the Somali Internet 🇸🇴

Comments
3 min read
How to Cut Regression Testing from Weeks to Hours Without Automating Everything

How to Cut Regression Testing from Weeks to Hours Without Automating Everything

2
Comments 1
12 min read
Generating test cases is the easy part

Generating test cases is the easy part

1
Comments
4 min read
Testing Google ADK TypeScript Agents Without Chasing Sentences

Testing Google ADK TypeScript Agents Without Chasing Sentences

1
Comments
5 min read
Probe vs Prose: what the verifier-sharing-your-text-channel really costs

Probe vs Prose: what the verifier-sharing-your-text-channel really costs

2
Comments 2
16 min read
Six things reported green and were lying

Six things reported green and were lying

1
Comments
4 min read
Our own CDN was 403-ing the official OpenAI SDK, and our test suite couldn't see it

Our own CDN was 403-ing the official OpenAI SDK, and our test suite couldn't see it

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