PulseAugur
实时 11:05:09
English(EN) Anthropic has apologised for one of the guardrails on its Fable 5 model, saying it was too restrictive and will be changed. Fable 5 is a nerfed version of the M

Anthropic 将修改 Fable 5 模型上过于严格的安全护栏

Anthropic 已承认其 Fable 5 模型上的一个安全护栏过于严格,并计划对其进行修改。Fable 5 是该公司 Mythos 模型的一个修改版本。该公司就此特定护栏施加的过度限制表示歉意。 AI

影响 对 AI 安全护栏的调整会影响模型行为和用户交互,可能影响负责任的 AI 部署。

排序理由 该集群讨论了对 AI 模型安全护栏的修改,属于 AI 安全研究和开发范畴。

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

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

    Anthropic has apologised for one of the guardrails on its Fable 5 model, saying it was too restrictive and will be changed. Fable 5 is a nerfed version of the M

    Anthropic has apologised for one of the guardrails on its Fable 5 model, saying it was too restrictive and will be changed. Fable 5 is a nerfed version of the Mythos model. https:// gizmodo.com/anthropic-apologiz es-for-one-of-the-guardrails-on-its-fable-5-model-and-will-change-i…

  2. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Anthropic Apologizes For One of the Guardrails on Its Fable 5 Model, and Will Change It https://gizmodo.com/anthropic-apologizes-for-one-of-the-guardrails-on-it

    Anthropic Apologizes For One of the Guardrails on Its Fable 5 Model, and Will Change It https://gizmodo.com/anthropic-apologizes-for-one-of-the-guardrails-on-its-fable-5-model-and-will-change-it-2000770365 # AI # Tech # Ethics