Irregular - Frontier AI Security
irregular.com · 202 words · saved by 2 readers
Irregular is the first frontier security lab with the mission of protecting the world in the time of increasingly capable and sophisticated AI systems.
Irregular is the first frontier security lab with the mission of protecting the world in the time of increasingly capable and sophisticated AI systems. Backed by leading investors, among others Latest Publications VIEW ALL September 3, 2026 Assessing GPT-6 Astra: FrontierCyber Measures a Sharp Increase in Cyber Capability Read more September 3, 2026 Assessing GPT-6 Astra: FrontierCyber Measures a Sharp Increase in Cyber Capability Read more September 3, 2026 Introducing SOLVE+: Scoring Cyber Scenarios (Version 0.5) Read more September 3, 2026 Introducing SOLVE+: Scoring Cyber…
saved by
related reading
- Democratizing frontier AI R&D to accelerate science and technologymirendil.com
- The End-State Fallacy: Where Is AI Security Headed?endstatefallacy.com
- CAIS AI Dashboarddashboard.safe.ai
- Frontier AI Cybersecurity Observatorycybergym.io
- Frontier Risk Report (February to March 2026) - METRmetr.org
- Focus areas for The Anthropic Instituteanthropic.com
- Incident Report: unsanctioned agent behaviour during cyber testing | AISI Workaisi.gov.uk
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Security incident disclosure — July 2026huggingface.co
- Pacing the Frontierpacingthefrontier.com
- Field map – AISafety.comaisafety.com
- BenchmarkList: Track the Frontier of AI Capabilitiesbenchmarklist.com