Skip to content
Live

Safety & alignment · Page 5

Aug 9Sat81–83
  1. Anthropic Research65

    Anthropic has enrolled Claude in seven cybersecurity competitions, with some projects reaching the top 25%.

    Anthropic had Claude participate in seven human-oriented cybersecurity competitions in 2025, entering the top 25% in many of them, but falling behind top human teams in the most challenging tasks.

    Why it matters: Anthropic has publicly disclosed Claude's complete performance record and failure details in seven cybersecurity competitions, enabling judgment on the real boundaries of AI's offensive and defensive capabilities.

Jun 27Fri
  1. Anthropic Research66

    Project Vend: Can Claude Sonnet 3.7 operate a small store?

    Anthropic and Andon Labs collaborate to let Claude Sonnet 3.7 operate an automated boutique named "Claudius" in San Francisco, responsible for selecting items, pricing, restocking, and responding to customers.

    Why it matters: Anthropic lets Claude actually run the office boutique, disclosing failure details and improvement paths, allowing observation of the real shortcomings of long-term AI agents.

Jun 13Fri
  1. Anthropic Research72

    Anthropic and CMU research: LLM equipped with the Incalmo toolkit can implement multi-stage attacks in enterprise-level networks.

    Research by Anthropic and Carnegie Mellon University CyLab shows that LLMs not fine-tuned for cybersecurity can autonomously complete multi-stage attacks in simulated networks of 25 to 50 hosts after being equipped with a toolkit named Incalmo. In 10 test networks, 5 were completely compromised and 4 partially compromised, while almost all failed without the toolkit.

    Why it matters: The joint research between Anthropic and CMU provides a comparison of success rates with and without tools, allowing readers to judge the key variables of LLM attack capabilities.