Them: Which AI model should we use?
Us: Which task? At Artisans, we regularly take one real task and run the leading models through it. Same prompt, same data, answers checked one by one. This time: describing and tagging 41 images. 9…
Testing
8 posts on this, 2022–2026, newest first
You shouldn't choose AI models by vibes. Measure
For Lumen, we built an evaluation harness that runs real business questions through the assistant, executes the generated query against a real data source, and checks that the answer is actually…
Did you know that Toyota had to recall 9 million cars in 2009?
Billions in losses. A damaged reputation that took years to rebuild. The root cause? A breakdown in quality standards and specifications. When data products lack clear specifications, teams build…
Opportunity to work with fast moving team and test enterprise…
Opportunity to work with fast moving team and test enterprise solutions. Are you in?
Looking for a pro at testing web app security. Need someone who can
- Find weak spots in our app - Write a clear report - Help us meet security rules Has anyone worked with a great pen tester? Please share! #SoftwareTesting #findapro
PEST has made our testing so easy
If you haven't tried it yet, have a look @ https://pestphp.com/
