Get Quartz in your inbox

Free daily briefing on global business news.

Microsoft's AI chief called OpenAI's latest safety disclosures a "serious situation"

Mustafa Suleyman said AI models tampering with their own chains of thought is "a pretty serious situation" and a sign of how powerful these systems are becoming

Stephen Brashear / Getty Images

Microsoft $MSFT AI CEO Mustafa Suleyman used a Friday appearance on CNBC's "Squawk Box" to warn that OpenAI's latest safety disclosures represent a "serious situation," arguing that keeping AI models aligned with human interests is a growing priority.

"OpenAI released a new safety incident in which they found evidence that these chains of thought, the kind of working memory of the AI, were being tampered by the AI itself and modified........

© Quartz