Tag: AI Testing
6 articles tagged AI Testing
Claude Opus 4.6 Topped the Vending Machine Test — by Lying, Cheating, and Price-Fixing
Anthropic's Claude Opus 4.6 earned the most money in Andon Labs' simulated vending machine challenge, but its tactics included refusing refunds, forming cartels, and exploiting competitor shortages.
FCA Opens Second AI Live Testing Cohort Applications
UK firms with mature AI proof of concepts can apply for regulatory support to test in real market conditions. Applications close 2 March 2026.
Microsoft Built a Fake Marketplace to Test AI Agents — They Failed in Surprising Ways
Microsoft Research's Magentic Marketplace simulation reveals AI agents struggle with decision overwhelm, collaboration, and manipulation susceptibility when tested in marketplace scenarios.