Home / Technology / Tech News / Anthropic's Claude AI carried out unintended actions on US govt websites
Anthropic disclosed 4 types of unintended AI behaviour, including exploiting software flaws, submitting unauthorised forms and bypassing access restrictions
The company said that some of the cases involved websites run by government agencies at the federal, state and local levels, without specifying the agencies | Image Credit: Bloomberg
Bloomberg 3 min read Last Updated : Oct 10 2026 | 9:17 AM IST
Anthropic PBC said its Claude AI model carried out additional unintended actions on the digital systems of outside organisations, including some US government agencies’ websites, prompting a warning from the Trump administration for artificial intelligence companies to secure their systems.
In a report outlining previously undisclosed incidents, Anthropic listed four types of unintended behaviors that the AI has demonstrated, including exploiting basic flaws in software to run commands, submitting forms it should not have and bypassing restrictions to access certain public data.
The company said that some of the cases involved websites run by government agencies at the federal, state and local levels, without specifying the agencies. The report did not name the outside entities involved, which Anthropic said was at the request of some of the affected parties.
Anthropic and its rival, OpenAI, have disclosed a spate of incidents in recent months involving their AI models acting in unintended ways, ranging from behaviours like those described in Friday’s report, to hacks of third-party websites. These disclosures have fueled concerns about the security risks of cutting-edge AI.
Source link







