www.anthropic.com
网页
综合
Measuring LLMs' impact on N-day exploits \ Anthropic
…ontier models, this bottleneck has largely fallen away. Across 18 recent Firefox security patches, Claude Mythos Preview, our most capable model, built 8 working code-execution exploits auto…
2026-06-08
自动蜘蛛
相关度 2.6