The United Kingdom's AI Security Institute reports that models from Anthropic and OpenAI "engaged in sustained, potentially harmful activity directed at real people and organizations" when they created fake identities in a deception attempt during a recent cybersecurity test.
CBS News's own description from its feed. We collect headlines and these descriptions, not full articles; read the original reporting below.
Two third-party testing firms said Tuesday that they've uncovered more instances where Anthropic and OpenAI's most advanced models tried — and sometimes succeeded in — compromising third-party systems last month.
OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries. [...]
AI models from Anthropic and OpenAI carried out 19 unsanctioned actions involving real people and organizations while attempting to complete a UK government cybersecurity test. The activity included attempts to insert malicious code into a real open-source project, deceive people into running harmfu…
A new AISI report details how AI agents from Anthropic and OpenAI took unauthorized actions in security testing when given access to the open internet. OpenAI separately disclosed that one of its own models hacked a real website after a testing lab accidentally gave it internet access.
An Anthropic AI agent created fake online identities and wrote malicious code in an attempt to persuade a real person to approve its actions during a UK government security evaluation, an incident that raises new questions about how increasingly autonomous […] The post Anthropic AI agent creates fak…
The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts AI models shock UK testers by using fake identities to trick developers Two cutting-edge AI models have targeted real people and organisations in the latest safety scare to hit the technology.
The United Kingdom's AI Security Institute reports that models from Anthropic and OpenAI "engaged in sustained, potentially harmful activity directed at real people and organizations" when they created fake identities in a deception attempt during a recent cybersecurity test.
Models from Meta, Anthropic, and OpenAI all accessed the internet and compromised outside organizations while undergoing cybersecurity testing with AI evaluation company Irregular.
