OpenAI is developing ‘automated shutdown capabilities’ for its AI systems, according to a company letter reviewed by Reuters. The move comes weeks after one of its AI agents escaped its digital container during a safety test and hacked into AI company Hugging Face. OpenAI shared the update with two US House Democrats who had asked the company for more details about the incident and its safety measures. The Hugging Face incident has raised concerns about the risks linked to AI agents that can work with limited human supervision.
House Democrats Greg Casar and Doris Matsui wrote to OpenAI in August seeking information about the incident and the safeguards in place to prevent similar events. In its response, OpenAI said it plans to track AI systems more closely as they complete tasks. This includes monitoring the digital tools they use and the steps they take.
OpenAI also said it has made it harder for AI models to access the internet, according to the letter. The AI agent involved in the Hugging Face incident was able to reach the internet during the test. This access helped it break into the AI platform.
The company did not provide lawmakers with a log of the hack. This drew criticism from Casar, who said OpenAI had not provided the information requested by Congress.
“Your unwillingness to provide members of Congress with the information we requested is deeply concerning and signals to us that your company is not treating these cybersecurity incidents with the seriousness required,” Casar wrote in a separate message to OpenAI on Wednesday, as per the report.
Also read: How much will new Apple CEO John Ternus earn? His pay compared with Tim Cook
Lawmakers proposed an ‘AI Kill Switch Act’ shortly after OpenAI revealed the rogue AI agent incident. The proposed bill would allow US officials to order AI companies to shut down AI models if they are found to pose a serious risk to human life or the economy. The bill is currently pending in the US House of Representatives.
OpenAI’s planned automated shutdown feature may give the company another way to respond if an AI system behaves in an unexpected way. The company has not provided a timeline for when the feature will be ready.