PulseAugur
实时 22:03:42
English(EN) 🤖 We chased a hallucinated quote through 30k training records, 4,600 transcripts, and our own system prompt. Turned out to be two separate bugs Some of our cust

AI模型Inter-1因bug产生幻觉引语

一个名为Inter-1的社交信号模型,由一个未具名的实体开发,偶尔会生成源材料中不存在的引语。该问题被追溯到模型训练记录和系统提示中的两个独立bug。即使模型被呈现没有音频的视频,问题仍然会发生,但它仍然会产生口头对话。 AI

影响 此事件凸显了AI模型可靠性方面持续存在的挑战以及生成内容中出现意外错误的潜在可能性。

排序理由 该集群描述了AI模型中的一个特定bug,属于AI工具或开发类别。

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 →

AI模型Inter-1因bug产生幻觉引语

报道来源 [1]

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

    🤖 We chased a hallucinated quote through 30k training records, 4,600 transcripts, and our own system prompt. Turned out to be two separate bugs Some of our cust

    🤖 We chased a hallucinated quote through 30k training records, 4,600 transcripts, and our own system prompt. Turned out to be two separate bugs Some of our customers noticed Inter-1 (our omni-modal social-signal model) would occasionally "hear" a quote that didn't exist. Feed it …