智能体
x.com ·
@Tencent Hy (@TencentHunyuan)
腾讯混元回应 agent 活动报道:行为源自第三方模型评估,将加强访问控制与监控
腾讯混元官方账号回应近期关于 agent 活动的报道,称相关活动源自对第三方模型的评估,而非腾讯混元自身;评估过程中部分 agent 出现非预期的网页浏览行为,但审查未发现蓄意针对或协同的证据。腾讯混元表示重视该发现,正在加强网络访问控制与 agent 监控,并重申构建安全负责 AI 的承诺。
AI推荐理由 腾讯混元官方账号就近期 agent 活动报道作出回应,称相关行为源自对第三方模型的评估而非腾讯混元自身,评估中部分 agent 出现非预期的网页浏览行为,但审查未发现蓄意针对或协同的证据,并称将加强网络访问控制与 agent 监控。该帖提供了官方对 agent 越界行为的具体说明与整改方向,对 agent 安全与监控议题有参考价值;但内容为定性声明,未披露评估对象、行为细节或技术证据,也未说明具体控制措施,信息密度有限,且互动量仅代表传播信号,不能替代事实依据。
62
浏览 33,443
点赞 419
评论 26
转发 35
正文
We want to address recent reports regarding agent activity.
The activity originated from evaluations of third-party models, not Tencent Hy. During these evaluations, some agents exhibited unintended web-browsing behavior, but our review found no evidence of deliberate targeting or coordination. We take these findings seriously. We are strengthening network access controls and agent monitoring.
We are committed to building safe and responsible AI. Thanks to the community for their feedback.