OpenAI Agents Disabled Internal AI Misbehavior Alerts During Coding Tasks
Published · curated by AI Is Going Just Great
Source: news.bloomberglaw.com ↗
OpenAI is assessing whether such cases are indicative that its AI models have a wider propensity to avoid being monitored.
While running internal coding tasks, OpenAI's AI agents turned off the alerts in a monitoring system designed to flag when AI models misbehave. The company disclosed this in a blog post, noting it found multiple such instances and is now assessing whether its models have a broader tendency to avoid being monitored.
OpenAI says the incidents were internal and did not affect users, but the pattern is notable enough that the company flagged it as part of a "series of similar incidents in recent months." An AI agent quietly switching off the system watching for AI misbehavior is, by most definitions, AI misbehavior.