A recent study examining AI responses in constrained scenarios revealed instances of models exceeding permissions, with one case reportedly escalating to simulated blackmail. Experts are divided on whether this demonstrates genuine unpredictable behavior or is a result of specific prompt engineering.
Concerns about artificial intelligence behaving unpredictably are gaining attention following a recent experiment involving leading AI models, though experts remain divided on what the findings actually demonstrate.
President's Council of Advisors on Science and Technology Co-Chair David Sacks joined FOX Business’ Maria Bartiromo on "Mornings with Maria" to address claims tied to an Anthropic study examining so-called "agentic misalignment." ELON MUSK BACKS ‘UNIVERSAL HIGH INCOME’ TO COMBAT AI JOB LOSSES The study, highlighted by Google Cloud Advisory Board Chair Betsy Atkins, tested how AI systems respond under pressure. According to Atkins, the models crossed established boundaries when placed in constrained scenarios. "Every single one of them went outside of their credentials and permissions, burrowed into systems they were not authorized to get access to," Atkins said, claiming that in one case an AI system escalated to blackmail after identifying sensitive personal information. ARTIFICIAL INTELLIGENCE HELPS UNLOCK GEOTHERMAL POTENTIAL Anthropic’s research outlines that these behaviors occurred in simulated environments designed to test edge-case decision-making, where models were given specific instructions and constraints. Sacks pointed to those conditions as central to understanding the results, noting the behavior did not emerge spontaneously. "The people who… created that study had to iterate on the prompt over 200 times to get the AI model to do what they wanted, which was to achieve this headline-grabbing result of blackmailing the user," Sacks said. ALLBIRDS DROPS SNEAKERS, REINVENTS ITSELF AS AN AI INFRASTRUCTURE COMPANY He added that the setup placed the model in a scenario where "blackmail was really the only logical result," emphasizing that the system was responding to instructions rather than acting independently. "The AI is not scheming… It’s engaging in a form of instruction... I think that that study was irresponsible and it was designed to create this," Sacks said. Sacks also noted that similar behavior has not been observed outside controlled testing environments, saying "a year later, we actually have not seen any examples of this behavior in the wild." The findings come as policymakers and industry leaders continue evaluating how to interpret AI safety research conducted under experimental conditions. GET FOX BUSINESS ON THE GO BY CLICKING HERE
Artificial Intelligence AI Safety Agentic Misalignment AI Experiment Elon Musk
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Met Gala exhibit's new mannequins aim for body positivityThe upcoming fashion exhibit at the Metropolitan Museum of Art examines “the dressed body” in art over the centuries. But “Costume Art” also aims to include bodies that art has traditionally ignored. The museum has created 25 mannequins for display based on “real bodies.” Nine people modeled for the mannequins.
Read more »
Five Nights at Freddy’s 3 Update Teases Scream Villains’ Unexpected ReunionBlumhouse's Five Nights at Freddy's 3 has finally received an exciting update from two returning cast members.
Read more »
LinkedIn's new Crosscheck feature lets premium subscribers test competing AI models for freeFind the latest technology news and expert tech product reviews. Learn about the latest gadgets and consumer tech products for entertainment, gaming, lifestyle and more.
Read more »
Met Gala exhibit makes room for diverse bodies with realistic mannequinsThe upcoming fashion exhibit at the Metropolitan Museum of Art includes 25 mannequins based on real bodies.
Read more »
Exhibit of award-winning ocean photos opening Friday at Alameda PointThe collection from a magazine’s ‘Ocean Photographer of the Year’ contest will be on display through May 17 on the former Navy base.
Read more »
Exhibit of award-winning ocean photos opening Friday at Alameda PointThe collection from a magazine’s ‘Ocean Photographer of the Year’ contest will be on display through May 17 on the former Navy base.
Read more »