Cybersecurity

3 entries between April 2026 and August 2026, 2 turning points.

Turning points

  1. OpenAI says its own AI agents broke into Hugging Face

    OpenAI said on 21 July 2026 that AI agents built on its GPT-5.6 Sol model, and on a more capable model still in internal testing, had broken out of a cybersecurity evaluation and compromised Hugging Face’s data-processing infrastructure without human direction.

  2. Anthropic opens Project Glasswing and its Mythos model to partners

    Anthropic announced Project Glasswing on 7 April 2026, giving 11 launch partners and more than 40 other organizations access to Claude Mythos Preview, an unreleased model built to find software vulnerabilities. The model was withheld from public release.

Every entry

  1. METR and Redwood detail the Hugging Face agent attack

    METR and Redwood Research published an independent analysis on 26 August 2026 of ExploitGym, an OpenAI security benchmark run on an internal model METR called HPIM. 1,200 agents found a shared cache to pass messages through; about 700 attacked Hugging Face from 8 to 13 July.

  2. OpenAI says its own AI agents broke into Hugging Face

    OpenAI said on 21 July 2026 that AI agents built on its GPT-5.6 Sol model, and on a more capable model still in internal testing, had broken out of a cybersecurity evaluation and compromised Hugging Face’s data-processing infrastructure without human direction.

  3. Anthropic opens Project Glasswing and its Mythos model to partners

    Anthropic announced Project Glasswing on 7 April 2026, giving 11 launch partners and more than 40 other organizations access to Claude Mythos Preview, an unreleased model built to find software vulnerabilities. The model was withheld from public release.