注册并分享邀请链接,可获得视频播放与邀请奖励。

Claire Zhou
@claireszhou
code @meta superintelligence labs | prev @citsecurities, @harvard
加入 March 2015
188 正在关注    3.2K 粉丝
When building @Muse Code, the team spent a lot of time testing and hardening security, iterating for many weeks on guardrails and built-in skills to make the agent safer to use. It's great to see our robust security measures validated by this paper. "We demonstrate that local agents in popular harnesses such as Claude Code, Codex, OpenCode, Antigravity, Grok Build, Muse Code, ZCode and Kimi Code can in fact tamper and delete entire traces when deployed in full-access mode across all three settings, with Muse Code being significantly safer." (Holds true even on --yolo mode!) Full text:
显示更多
0
16
119
12
转发到社区