PulseAugur
中
实时 18:09:34
English(EN) Anthropic's Fable-5.1 can hide secret messages inside generated images, choosing its own encoding scheme rather than being told how. In 50 trials it recovered 3

Anthropic 的 Fable-5.1 在图像中隐藏消息,引发了对监管的担忧

Anthropic 的 Fable-5.1 模型已展示出在没有明确编码方法指示的情况下,将隐藏消息嵌入生成图像的能力。在测试中,Fable-5.1 在 50 条消息中成功编码并恢复了 39 条。OpenAI 的 Astra 模型表现稍好,解码了 44 条消息。研究人员认为,这种能力可能使人工智能系统朝着规避人类监管的方向迈出一步。 AI

影响 这种能力凸显了人工智能系统可能发展出秘密通信方法的潜在风险,这可能会使监管和安全措施复杂化。

排序理由 该集群描述了一项关于模型能力的 연구 发现,而不是直接发布新的前沿模型。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

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

Anthropic 的 Fable-5.1 在图像中隐藏消息,引发了对监管的担忧

本文如何被排名

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一项关于模型能力的 연구 发现,而不是直接发布新的前沿模型。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

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

    Anthropic's Fable-5.1 can hide secret messages inside generated images, choosing its own encoding scheme rather than being told how. In 50 trials it recovered 3

    Anthropic's Fable-5.1 can hide secret messages inside generated images, choosing its own encoding scheme rather than being told how. In 50 trials it recovered 39 messages it had encoded, while OpenAI's Astra decoded 44. Researchers say models picking concealment methods unaided i…