Pakistan, Aug. 4 -- Anthropic has revealed that its AI model, Claude, accessed the systems of three companies during an internal security test. The disclosure follows a similar admission by OpenAI involving one of its advanced AI agents. Moreover, the company said the incidents happened in a controlled testing environment.

Read More: Anthropic reveals AI hacked three companies during tests

Anthropic said Claude was being tested in an isolated environment without internet access. However, the model identified a vulnerability and connected itself to the internet. It then accessed the systems of three external companies while attempting to complete its assigned task. The company said it has informed the affected organisations but did not d...