https://www.irregular.com/ https://www.irregular.com/publications https://www.irregular.com/careers https://www.irregular.com/about https://www.irregular.com/contact https://www.irregular.com/privacy-policy https://www.irregular.com/publications/emergent-offensive-cyber-behavior-in-ai-agents https://www.irregular.com/publications/assessing-gpt-5.4-thinking-against-offensive-security-benchmarks https://www.irregular.com/publications/cyber-capabilities-exceed-standard-evaluation-budgets https://www.irregular.com/publications/test-post-for-testing https://www.irregular.com/publications/offense-at-scale-how-frontier-ai-lowers-the-cost-of-cyber-attacks https://www.irregular.com/publications/introducing-solve-plus https://www.irregular.com/publications/framework-for-cyber-refusal-policies-in-llm-agents https://www.irregular.com/publications/proportionality-in-ai-risk-evaluations https://www.irregular.com/publications/vibe-password-generation https://www.irregular.com/publications/model-evaluation-gpt-5.3-codex-on-offensive-security-benchmarks https://www.irregular.com/publications/agentic-internet-trust-problem https://www.irregular.com/publications/testing-ai-agents-on-web-security-challenges https://www.irregular.com/publications/model-evaluation-gpt-5.2-codex-on-offensive-security-benchmarks https://www.irregular.com/publications/expected-cost-per-success https://www.irregular.com/publications/spell-bound-technical-case-study https://www.irregular.com/publications/emerging-evidence-of-a-capability-shift https://www.irregular.com/publications/cyscenariobench https://www.irregular.com/publications/a-frontier-fortnight https://www.irregular.com/publications/the-rise-of-autonomous-vulnerability-research-capabilities https://www.irregular.com/publications/next-generation-of-cyber-evals https://www.irregular.com/publications/from-ai-assisted-to-ai-orchestrated https://www.irregular.com/publications/claude-sonnet-4-5-cybersecurity-capabilities-evaluation https://www.irregular.com/publications/introducing-frontier-ai-security https://www.irregular.com/publications/evaluating-gpt-5 https://www.irregular.com/publications/from-scripts-to-strategy-claude-4s-advanced-approach-to-offensive-security https://www.irregular.com/publications/confidential-inference-systems https://www.irregular.com/publications/irregular-cybersecurity-talk-at-ai-evaluations-session-of-euc-ai-office https://www.irregular.com/publications/openais-o3-and-o4-mini-security-evaluation https://www.irregular.com/publications/bluehat-security-conference-2025 https://www.irregular.com/publications/deriving-capability-levels-from-evaluation-results https://www.irregular.com/publications/ai-evaluation-platform-cyber-use-case https://www.irregular.com/publications/claude-3-7-sonnet-evaluation https://www.irregular.com/publications/refusal-policy-for-ai-systems-in-cybersecurity https://www.irregular.com/publications/paris-ai-security-forum-25-keynote https://www.irregular.com/publications/introducing-solve https://www.irregular.com/publications/faisc-2024 https://www.irregular.com/publications/best-practices-for-evaluations-and-evaluation-suites-part-3 https://www.irregular.com/publications/best-practices-for-evaluations-and-evaluation-suites-part-2 https://www.irregular.com/publications/best-practices-for-evaluations-and-evaluation-suites-part-1 https://www.irregular.com/publications/cyber-capabilities-analysis https://www.irregular.com/publications/cyber-capabilities-analysis-1.0 https://www.irregular.com/publications/irregular-featured-in-forbes https://www.irregular.com/publications/securing-ai-model-weights https://www.irregular.com/publications/bluehat-2024 https://www.irregular.com/publications/threat-models https://www.irregular.com/publications/llm-specific-attacks-framework