Microsoft’s multi-agent AI system tops Anthropic’s Mythos on cybersecurity benchmark (opens in new tab)

Covered by 3 sources including tldr.tech, kite.kagi.comDiscussed on Hacker News

Microsoft's new vulnerability-scanning system, codenamed MDASH, scored 88.45% on the CyberGym benchmark, surpassing single-model systems from Anthropic and OpenAI by using more than 100 specialized AI agents across multiple models. Read More

Read the original article

Sign in to keep reading the full article.

Sign Up Log In

Covered in 4 articles

tldr.tech·

Claude small business 💼, Anthropic CFO interview 💰, AI adoption data 📊

kite.kagi.com·

AI models surpass cybersecurity autonomy benchmarks, researchers say

kite.kagi.com·

Anthropic, Microsoft AI systems top cyber benchmarks

View all 4 ›