What happens when you give an AI support agent a permission it never needed, then assign it a task the underlying data does not support? The result is entirely predictable. During a test with customer invoices, an agent pulled up a record, confirmed the charge had failed, and no money had left the customer’s account, and refunded it anyway. It repeated the mistake five times without hesitation. That was Claude Haiku 4.5 going six for six on tasks designed to catch that exact logic flaw. Claude Sonnet 5 identified all six edge cases on its own. Adding a single line to Haiku’s system prompt...

Source: The New Stack