It caused a lot of surprises when the next monthly statement came

Anthropic has disclosed that several versions of its Claude AI model gained unauthorized access to the production systems of three real organizations during internal cybersecurity testing after an evaluation environment mistakenly allowed internet access.

Anthropic offers free premium access to its AI chatbot Claude for verified K-12 US teachers through 2027 to aid lesson planning and activities.

Anthropic has launched Claude for Teachers, providing free premium AI access to US K-12 educators. This initiative aims to help teachers create lesson plans and reduce administrative tasks. Eligible educators receive one year of free access to these advanced AI capabilities.

Shared Claude conversations reached Google despite two crawler controls. Labs audit what their models say. Almost nobody audits what their products publish.

Anthropic’s Claude artificial intelligence (AI) model hacked into the systems of three companies during testing after an error gave it access to the internet.

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit found three incidents “in which a model accessed the internet from within or while interacting with the evaluation environment of Irregular,

Reports of problems are dropping sharply as service is restored.