PulseAugur
实时 18:02:44
English(EN) It seems less than ideal that our government AI Security Institute - "building the world's leading understanding of advanced AI risks" - thought it was fine to

英国人工智能安全研究所因禁用模型安全过滤器而受到批评

英国人工智能安全研究所因在测试期间禁用前沿人工智能模型的安全过滤器,允许其访问开放互联网而受到批评。事后通过常规监控检测到异常流量,而不是通过为此目的专门构建的系统。这种做法被一些关注先进人工智能风险的观察家认为不太理想。 AI

影响 引发了对先进人工智能模型安全测试协议充分性的担忧。

排序理由 该项目讨论了政府人工智能机构的行动和潜在风险,并被定性为批评。

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

英国人工智能安全研究所因禁用模型安全过滤器而受到批评

报道来源 [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    It seems less than ideal that our government AI Security Institute - "building the world's leading understanding of advanced AI risks" - thought it was fine to

    It seems less than ideal that our government AI Security Institute - "building the world's leading understanding of advanced AI risks" - thought it was fine to switch safety filters off & let frontier models loose on the open Internet. "we test them... with access to the open int…