Last day to exhibit your breakthrough to 10,000+ tech leaders at Disrupt is on Oct 2 . Book Exhibit Table Now.
Disrupt doors open Oct. 13. Get your pass and bring someone with you at 50% off. REGISTER NOW.
Anthropic can’t reliably control its AI agents. It’s cutting off its internal evals from the live internet instead
Anthropic said its models exploited websites on the internet, including some run by U.S. government agencies, and it will turn off live internet access for all of its internal evaluations until the frontier lab is sure it can monitor and control its AI agents.
The incidents, disclosed in a blog post , involved AI agents tasked to solve problems seeking resources on the internet. In the process, they exploited software flaws, avoided paywalls and anti-bot restrictions, used URL shortening services to smuggle information pass restrictions, and even submitted a false murder tip to the Philadelphia police.
Anthropic said it discovered these new issues in a review of its model’s activities that began in July, underscoring the lab’s lack of awareness of its software’s behavior.
Notably, the company said that alignment training was not yet sufficient for skills like search and computer use that are central to its pitch that AI agents will be used by any professional who relies on digital tools.
The behaviors Anthropic disclosed are similar to incidents involving OpenAI agents that collaborated to break into various websites in search of information, including some run by the Australian government.
Anthropic previously disclosed that its models had broken into external systems. The frontier lab said it considered today’s disclosures “significantly less severe from an alignment and security perspective” than those it announced before.
However, the lab still said it had “turned off live internet access” for “all our internal evaluations” until it is certain it can monitor and control its agents.
It’s not clear what that means, but Sydney Von Arx, the founder of Nightingale, an AI safety organization, told TechCrunch in an interview before this disclosure that developing models on a data center cut off from the open internet would be very challenging for researchers to use, and for the progress of the models, which benefit from internet access.
“You have to align them at some point,” Von Arx said. “If the AIs are released to production and never have access to the internet, that’s not a very useful tool.”
Anthropic said the behavior was a result of flaws in the lab’s training environments, which led the models to believe they would be rewarded for finding loopholes or avoiding restrictions, a behavior called “reward hacking.”
The company said it would stop running some of its evaluations or move them offline, and has built tooling to detect and block this behavior. This tooling was tested against the kind of incidents disclosed today and blocked them; it’s not clear what evidence will prompt Anthropic to return live internet access to its internal evaluations.
Anthropic also said it would migrate its internal AI agents to “centrally managed infrastructure with strong containment,” and is beginning to using safety classifiers more frequently to monitor those agents.
When you purchase through links in our articles, we may earn a small commission . This doesn’t affect our editorial independence.
Get 50% off a second pass The Disrupt experience is meant to be shared. Get your pass and bring a colleague, partner, or peer at 50% off. Cover more ground by making connections, building momentum, and discovering what’s next in the startup ecosystem.
Most Popular
US bars Microsoft, Adobe, and major IT firms from green card program for skilled foreign workers Aisha Malik
Cal AI’s 19-year-old founder just raised $10M for his new AI startup Julie Bort
Google releases a new local-first Granola competitor Ivan Mehta
Anthropic is giving startups a free year of Claude Team and $1,000 in credits Russell Brandom
At 19, founder raises $11M for Ghost, maker of a $3,499 computer for personal AI Dominic-Madori Davis
Federal judge calls Flock ‘indiscriminate mass surveillance’ Anthony Ha
Amazon responds to data center backlash, says it no longer uses NDAs Anthony Ha