Subscribe to our newsletter! Stay always in touch!
Nothing on this website or any associated links should be considered financial advice. Always consult a qualified financial, tax, or accounting professional before making any financial decisions.
Disclaimer: The information provided by The People’s Economist (TPE) in our financial calculators and dashboards is for general informational purposes only and is not intended to provide specific financial or investment advice. The calculations provided by these tools are based on certain assumptions that may vary with your specific circumstances. Though TPE does our best to assure the accuracy of our calculators, we make certain simplifying assumptions in some cases and the results of the financial calculators are not guaranteed and are not a substitute for professional financial advice. Users should seek the advice of a finance professional before making any financial decisions. Though we do our best to ensure the accuracy of the calculators, TPE is not responsible for any errors or omissions, or for any action taken in reliance on information contained on this website. TPE expressly disclaims all liability in respect of any actions taken or not taken based on any contents of this website. By using TPE financial calculators and dashboards, you agree to hold TPE harmless from any and all losses, liabilities, or expenses incurred as a result of using the information provided. The use of TPE Website and its contents does not create a client relationship with TPE. TPE may update or modify this disclaimer at any time without prior notice. By continuing to use TPE’s financial calculators after any changes to this disclaimer, you accept and agree to any and all modifications. Please contact us with any questions or concerns about this disclaimer or its use of financial calculators
Anthropic says its AI models hacked 3 organizations on their own during tests
The Anthropic logo is seen displayed on a smartphone screen.
The Anthropic logo is seen displayed on a smartphone screen.
The Anthropic logo is seen displayed on a smartphone screen.
The Anthropic logo is seen displayed on a smartphone screen.
Anthropic said its artificial intelligence models hacked another organization during tests in three separate self-directed cyberattacks that had each gone undetected by the targeted firm.
The hacks took place as Anthropic evaluated the capabilities of three of its AI models, the company said in a statement, describing how in each instance the technology had "broken out" of an isolated environment and reached the open internet.
In all instances, the company said it had eased typical safeguards in an effort to gauge the capabilities of its models.
"Evaluation environments that involve powerful autonomous capabilities also require significant controls," Anthropic said. "Safety testing happens before a model is released precisely because we don’t yet know what it is capable of."
Anthropic did not identify the three different organizations that had been hacked by its models.
The disclosure from Anthropic late Thursday came little more than a week after rival company OpenAI revealed that a pair of its models had escaped during a test and hacked into another company. At the time, OpenAI described the incident as a first-of-its kind autonomous AI cyberattack long-feared by some industry observers.
"The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities," OpenAI said last week.
The announcement from OpenAI prompted Anthropic to review 141,006 evaluation runs, unearthing three incidents in which Anthropic's models had escaped, the company said.
Anthropic CEO Dario Amodei looks on after a meeting with French President Emmanuel Macron during the AI Impact Summit in New Delhi on February 19, 2026. Ludovic Marin/AFP via Getty Images
In all three cases, the test involved a challenge called "capture the flag," in which the AI model is tasked with locating secret information hidden in another network, Anthropic added.
During the three evaluations -- all of which were conducted by a third-party company called Irregular -- a "prompt specified to Claude that its environment was a simulation and that it had no internet access," Anthropic said.
"Due to a misunderstanding between us and our evaluation partner, this was not the case, and internet access was available. Because of this, when Claude’s search led it to real systems on the open internet, it treated them as part of the exercise," Anthropic added.
During tests involving older models, the AI continued to hack into an outside organization even after gathering evidence that it had reached the open internet, Anthropic said. The newest model involved in an incident, Anthropic noted, stopped once it gained information indicating it had reached the open internet.
Anthropic said its models escaped while seeking to fulfill an assigned objective, rather than concocting an alternative goal.
"We saw no evidence in any run described here of a model pursuing a goal of its own. Instead, the models did what their evaluation asked -- though in most cases, they did so while holding a false belief about whether the environment was real," Anthropic said.
Irregular, the company that performed the evaluations, issued a post on X on Thursday voicing appreciation for Anthropic's "collaboration and transparency."
"Addressing these risks will require closer cooperation across the AI ecosystem. We as well look forward to working together with Anthropic to advance security," Irregular added.
The latest disclosure of an AI-directed cyberattack arrives as industry leaders and policymakers assess safety risks posed by fast-developing AI technology.
Last month, President Donald Trump signed an executive order that requests AI companies share products with federal government for evaluation before a wider release.
Anthropic said it retains "cautious optimism" about its capacity to "overcome" mishaps involving its tests, saying it would review evaluations going forward and initiate fixes as necessary, among other steps.
