clem 🤗(@ClementDelangue):"But here is what we found when we tested: We took the specific vulnerabilities Anthropic showcases in their announcement, isolated the relevant code, and ran them through small, cheap, open-weights models. Those models recovered much of the same analysis. Eight out of eight models detected Mythos's flagship FreeBSD exploit, including one with only 3.6 billion active parameters costing $0.11 per million tokens. A 5.1B-active open model recovered the core chain of the 27-year-old OpenBSD bug."

clem 🤗

@ClementDelangue

Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders

加入 September 2010

4.9K 正在關注 300.3K 粉絲

clem 🤗@ClementDelangue

2026.04.08 18:58

"But here is what we found when we tested: We took the specific vulnerabilities Anthropic showcases in their announcement, isolated the relevant code, and ran them through small, cheap, open-weights models. Those models recovered much of the same analysis. Eight out of eight models detected Mythos's flagship FreeBSD exploit, including one with only 3.6 billion active parameters costing $0.11 per million tokens. A 5.1B-active open model recovered the core chain of the 27-year-old OpenBSD bug."