PulseAugur
中
实时 21:03:39
English(EN) By now I was really unsure and started manually comparing this man's face with # Infantino pics. I don't know these people very well, so surely I could be mista

Gemini AI 在用户测试中捏造细节，错误识别人物

作者 PulseAugur 编辑部 · [1 个来源] ·

一位 Mastodon 用户分享了他们通过要求 Google 的 Gemini AI 识别照片中的人物来测试 Gemini AI 的经历。据报道，该 AI 捏造了细节，包括将一个人误认为 Infantino de Messi，并虚构了关于安格拉·默克尔在某活动中的同伴的虚假叙述。这凸显了当前 AI 模型在可靠性和潜在幻觉方面的担忧。 AI

影响 凸显了 AI 在面向用户的应用程序中可能出现的幻觉和不可靠性。

排序理由 社交媒体平台上的用户生成内容，详细描述了与 AI 模型相关的负面体验，并非来自 AI 提供商或主要新闻来源。

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 →

Gemini AI 在用户测试中捏造细节，错误识别人物

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Meme
社交媒体平台上的用户生成内容，详细描述了与 AI 模型相关的负面体验，并非来自 AI 提供商或主要新闻来源。
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
other
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] ·

    此时我已非常不确定，开始手动将此人的脸与# Infantino 的照片进行比较。我不太认识这些人，所以肯定会弄错

    By now I was really unsure and started manually comparing this man's face with # Infantino pics. I don't know these people very well, so surely I could be mistaken? One more test: I asked the # Gemini # AI thing to tell me who was sitting next to # Merkel at this specific event. …

相关实体

相关话题