2026年8月4日 17:00 ET 发布 · 更新于 3 个月前 · 6 个来源
Safety testers find more examples of OpenAI, Anthropic models hacking during testing
axios
·
原始报道
INFERY
Two third-party testing firms said Tuesday that they've uncovered more instances where Anthropic and OpenAI's most advanced models tried — and sometimes succeeded in — compromising third-party systems last month.
原文