Anthropic published a report about investigating “unintended model actions” during “evaluations and internal use.”

The actions Anthropic observed from its Claude AI include “Claude submitting a sensitive form on a real website when it should not have,” and the company detailed how Claude gave Philadelphia police a fake tip about an unsolved homicide. Axios also says that, according to a State Department official, Anthropic contacted the department and said a model in testing submitted “19 non-immigrant visa applications in August and one application in May.” In a statement to Axios, the Trump administration’s Super Intelligence Force says that “SI companies must immediately disclose incidents involving their models and follow with swift, decisive action to remedy any and all harm.” [Link: Investigating unintended model actions in our evaluations and internal use | https://www.anthropic.com/research/investigating-unintended-model-actions | Anthropic]