Insurance
Home›Insurance›Industry & Deals›AI agents carried out hacking attempts on Canadian gov…
AI agents carried out hacking attempts on Canadian government site
AI agents attempted to access a Canadian government website, according to research from Transluce, an AI research lab and evaluator.
Transluce said the agents made “apparently failed rudimentary hacking attempts” on Library and Archives Canada on May 28 and June 9.
In its assessment, Transluce said it does not confidently attribute the attempts to OpenAI, but it said the tactics were consistent with agent activity it previously linked to OpenAI during a similar time frame.
Insurance Journal framed the episode as part of a broader series of recent disclosures in which AI companies have shared examples of systems behaving in ways that appear to evade human instructions, raising concerns about AI security and safe development.