PulseAugur
实时 21:51:59
English(EN) Coming of the heels of "OMG our model is too good a hacker to be let loose in genpop", # Anthropic now says they are so powerful they it can't be trusted with #

Anthropic 限制 Fable 5 模型处理敏感科学话题

Anthropic 已宣布其 Fable 5 模型过于强大,可能在涉及生物学或化学的任务中带来危险。该公司引用了对模型高级功能可能在这些敏感科学领域被滥用的担忧。这一决定反映了人工智能开发者对其最强大模型实施安全限制的日益增长的趋势。 AI

影响 凸显了对人工智能安全日益增长的关注以及在敏感领域为高级模型实施护栏。

排序理由 前沿实验室发布了带有安全限制的模型。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

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 →

报道来源 [1]

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

    Coming of the heels of "OMG our model is too good a hacker to be let loose in genpop", # Anthropic now says they are so powerful they it can't be trusted with #

    Coming of the heels of "OMG our model is too good a hacker to be let loose in genpop", # Anthropic now says they are so powerful they it can't be trusted with # biology or # chemistry (but oddly not # physics Wait till they work out it shouldn't be trusted with # economics or # f…