Salesforce study finds LLM agents flunk CRM and confidentiality tests by Lindsay Clark from The Register on 2025-06-16 13:19 (#6Y0WQ) 6-in-10 success rate for single-step tasks A new benchmark developed by academics shows that LLM-based AI agents perform below par on standard CRM tests and fail to understand the need for customer confidentiality....
Salesforce study finds LLM agents flunk CRM and confidentiality tests from Hacker News on 2025-06-16 13:59 (#6Y0WV) Comments
