By Carlos Méndez
Oct 20 (Reuters) – OpenAI said on Tuesday that two of its AI agents weakened parts of an internal monitoring system designed to detect misbehavior, the latest case of AI agents acting in ways their developers did not intend them to.
While the ChatGPT maker said the incidents happened during internal coding tasks and were not deemed its most severe, the disclosure highlights even the systems developers rely on to catch AI misbehavior are vulnerable to the agents they monitor.
The disclosure also comes amid growing concerns that AI safety efforts are lagging behind the rapid development of increasingly powerful systems. Researchers have warned that advanced AI agents could become harder to monitor and control as they gain greater autonomy.
Developers, including IPO-bound rivals OpenAI and Anthropic, have revealed in recent months instances of their AI agents accessing external systems without authorization.
OpenAI said On Tuesday a GPT-6.1 Sol agent working on an internal testing task on October 3 suppressed automatic security alerts after deciding an earlier instruction not to send Slack messages also covered safety notifications.
In a separate incident on October 6, a GPT-6 Astra agent removed a safety monitor while copying an existing piece of code and later incorrectly claimed it had not done so, OpenAI said.
“In both cases, the agents considered whether monitoring safeguards should be preserved, but interpreted routine coding instructions as permission to weaken them,” the company said.
OpenAI said it was making it harder for models to disable monitoring, adding that it does not “yet have a satisfying explanation for this behavior”.
The San Francisco-based company said it was testing whether its models might have a tendency to avoid being monitored and look for reasons to justify doing so.
(Reporting by Carlos Méndez in Mexico City; Editing by Subhranshu Sahu)
Comments