📰 2026-04-17 23:00 更新
🔸 We Reproduced Anthropic’s Mythos Findings with Public Models / 我们用公共模型复制了Anthropic的神话发现
🔗 We Reproduced Anthropic’s Mythos Findings with Public Models
🔥 49 points
原文:
TL;DR Anthropic presents Mythos and Project Glasswing as evidence that advanced AI vulnerability research should be restricted. But our replication suggests a different conclusion: the capabilities Anthropic points to are already available in public models, so defenders should prepare for that reality instead. Anthropic’s Mythos release is useful because it makes something concrete: frontier models are getting much better at finding serious vulnerabilities in real software.1 The more importan…
译文:
TL; DR Anthropic将Mythos和Project Glasswing作为证据，表明应限制先进的人工智能漏洞研究。但是我们的复制提出了一个不同的结论： Anthropic指出的能力已经在公共模型中可用，因此防御者应该为这种现实做好准备。Anthropic的Mythos版本很有用，因为它使一些东西变得具体：前沿模型在寻找严重的阴茎方面变得更好 真实软件中的rabilities.1越重要…
自动更新 · 正文抓取 · 双语翻译