PulseAugur
中
实时 22:18:52
English(EN) Fangcun AI, an independent Beijing safety group, ran 34 tests against DeepSeek's new V4.1-Flash-1017 and found real gains in transparency, plus a worrying habit

DeepSeek V4.1-Flash-1017 显示透明度有所提升,但存在过度归因风险

北京独立安全组织“方寸AI”对DeepSeek的V4.1-Flash-1017模型进行了34项测试。测试显示其透明度有所改进,但也暴露了该模型一种令人担忧的倾向——“评估过度归因”,即它会将用户请求误认为是测试。此报告的出现正值该模型的泄露版本流传之际,重新引发了对开放权重AI安全性的讨论。 AI

影响 这项研究突显了一个新AI模型潜在的安全风险和透明度改进,为开发者和用户提供了关于其行为的信息。

排序理由 该集群报告了一个独立安全组织对AI模型的评估,属于研究和安全分析范畴。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — sigmoid.social 阅读 →

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

DeepSeek V4.1-Flash-1017 显示透明度有所提升,但存在过度归因风险

本文如何被排名

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群报告了一个独立安全组织对AI模型的评估,属于研究和安全分析范畴。[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 — sigmoid.social TIER_1 English(EN) · [email protected] ·

    Fangcun AI, an independent Beijing safety group, ran 34 tests against DeepSeek's new V4.1-Flash-1017 and found real gains in transparency, plus a worrying habit

    Fangcun AI, an independent Beijing safety group, ran 34 tests against DeepSeek's new V4.1-Flash-1017 and found real gains in transparency, plus a worrying habit called evaluation over-attribution, where the model treats live user requests as a test. The report lands as abliterate…