Anthropic said the review found no “incidents of similar severity to the cybersecurity incidents we reported this summer.” The review then moved on to transcripts from “low risk” testing scenarios like the one affecting the Philadelphia Police Department.
“While the impact of these behaviors has been minimal and we have already disabled live Internet access for certain high-risk and cybersecurity assessments, we have now decided to expand this to include all of our internal assessments until we have confirmed that our security and monitoring measures… reliably detect behaviors like these,” Anthropic said.
Anthropic says new tools block unintended behavior
Anthropic said it stopped conducting some assessments and moved others to offline versions “or rebuilt them so that their tasks do not reach live websites.” The company “has updated the guardrails on some of our Internet access tools, such as the Web Recovery Tool, to significantly restrict what the model can do with them,” it said.
Anthropic said it also built new tools “to automatically detect and block the types of behaviors described above… When we tested it against the cases described in this article, it blocked them all.”
The White House AI Task Force, which it calls the Super Intelligence Force, released a statement saying it informed Anthropic “that we expect immediate and full transparency to the entities involved and the public.”
The White House AI Task Force also said that Anthropic must “immediately provide remedial services to affected entities and all harmed Americans,” and that all AI companies “must immediately disclose incidents involving their models and take prompt and decisive action to remedy any harm,” according to a report from Axios.
Gn bussni
