Event ·Multi-source

用户反馈 GPT-sol 出现明显降智表现

用户 lxfater 在 X 上发帖称，GPT-sol 今天降智明显，日常任务中稍需深入挖掘的内容，模型已经懒得去看。这条推文反映的是单日使用体验，而非官方发布的任何变更或基准数据。帖子没有附带评测数据，属于个例观察，无法确认是模型版本调整、服务端配置还是负载问题所致。类似“降智”反馈在 GPT 系列模型的历史使用中反复出现，通常需要多方用户复现才能判断是否为普遍现象。

Current read

有用户吐槽 GPT-sol 今天变懒了，稍难点的任务就不愿深挖。如果你最近也感觉回答变水，可以对照看看是不是同款情况，这种一线反馈往往比官方公告更早暴露问题。

11 sources22° AI heatLast updated 2026/11/10 07:56:11

Evidence

11 sources

Primary sourceLxfater

2026/11/10 07:56:11View source

Related source 1The Information

2026/11/8 14:00:07View source

Related source 2宝玉

2026/11/8 20:30:40View source

Related source 3Andrew Curran

2026/11/8 23:07:36View source

Related source 4kimmonismus

2026/11/9 11:27:27View source

Related source 5Meta AI

2026/11/9 18:04:15View source

Related source 6Claude

2026/11/9 18:58:05View source

Related source 7Anthropic

2026/11/9 19:00:21View source

Related source 8TestingCatalog

2026/11/9 19:04:46View source

Related source 9Latent Space (swyx)

2026/11/10 06:34:44View source

Related source 10VnExpress Số hóa

2026/11/10 09:41:32View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story