Skip to content
Hot storiesContinuously updated

实测显示主流大模型存在电商价格幻觉及联网搜索失效问题

1 reports1 reporting sourcesUpdated 17 hours ago

Start here

AI overview

2026年11月3日,针对大模型在报价时频发的幻觉问题,相关实测结果显示,gpt-6-luna 与 Claude Opus 5.5 在电商价格测试中表现不佳。两款模型仅凭自身记忆在 15 款商品中仅答对 2 个实时价格;更进一步的测试显示,即使启用了内置联网搜索功能,模型在附带参考链接的情况下依然会出现价格错误,表明单纯依靠记忆或内置搜索仍难以解决 AI 智能体的电商价格幻觉。

AI-generated from reports · Updated 17 hours ago

Report timeline

Follow the reports to see different sides of the story.

Nov 3
  1. Hacker News · AI
    如何用实时数据 Grounding 解决 AI 智能体的电商价格幻觉

    针对大模型在报价时频发的幻觉问题,实测显示 gpt-6-luna 与 Claude Opus 5.5 仅凭记忆在 15 款商品中仅答对 2 个实时价格,即使启用内置联网搜索也依然会在附带链接的情况下出现错误。

Story heat trend

Current heat 6·Comparable peak 10(Nov 3 19:00)·Comparable change, last 24 hours–

02.557.510Nov3Nov4Nov4Nov4

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.