Stanford Paper: API Audits Don't Reflect Real Chatbot User Experience

A Stanford-led EMNLP paper auditing seven AI systems finds that safety audits conducted via APIs do not transfer to consumer chatbot interfaces, meaning API-based audits may misrepresent what real users experience.

2026-09-16 ~ 2026-09-16 · 2 related posts

• Study: API-based audits of ChatGPT, Claude and Gemini don't transfer to chatbot UIs — kenziyuliu · 2026-09-16
• Stanford EMNLP paper: API-level audits don't reflect what chatbot users actually get — StanfordAILab · 2026-09-16