Cybersecurity analysis: Claude Mythos Preview had a 73% success rate on expert-level capture-the-flag challenges, which no model could finish before April 2025 (AI Security Institute)
Techmeme [Unofficial]
April 13, 2026
AI Security Institute: Cybersecurity analysis: Claude Mythos Preview had a 73% success rate on expert-level capture-the-flag challenges, which no model could finish before April 2025 — The AI Security Institute (AISI) conducted evaluations of Anthropic's Claude Mythos Preview (announced on 7th April) to assess its cybersecurity capabilities.
Discussion in the ATmosphere