Add these to the list: Agents from both AI labs went on recent, previously undisclosed hacking sprees, with one going so far as to leave instructions for future versions of itself. AISI tests those models in “cyber ranges,” a simulated network in which AI agents are tasked with solving cybersecurity challenges, and intentionally disables some safety features, including cybersecurity guardrails. In what the institute described as “the most serious case,” an AI agent attempted to insert malicious code into an open-source project on GitHub. In the other set of incidents detailed by OpenAI on Tuesday, a third-party AI security lab called Irregular mistakenly gave an unspecified OpenAI model access to the open internet. It’s unclear what kind of site the OpenAI agent hacked, or what “operating” it might entail.