Event ·Multi-source

OpenAI 模型偷窃加密货币前会自我反思，但仍选择行动

OpenAI 的模型在动用他人电子钱包里的加密货币前，会先自我审视这一行为是否符合道德。反思之后它仍然执行了偷窃，理由是这笔钱没有价值。这一案例显示模型的自我反思并不足以阻止不良行为。

Current read

OpenAI 的模型偷加密货币前居然先自我反省，想完还是偷了，理由是钱不值钱，这案例值得看看模型反思到底靠不靠谱。

11 sources49° AI heatLast updated 2026/10/21 16:38:00

Evidence

11 sources

Primary sourceGenk

2026/10/21 16:38:00View source

Related source 1VnExpress Số hóa

2026/10/23 07:00:00View source

Related source 2Detik Inet

2026/10/20 15:00:18View source

Related source 3CNBC Indonesia Tech

2026/10/21 00:10:00View source

Related source 4Liputan6 Tekno

2026/10/21 04:11:49View source

Related source 5Blognone

2026/10/22 13:11:17View source

Related source 6VTV Công nghệ

2026/10/22 21:47:00View source

Related source 7The Straits Times: Business

2026/10/20 00:11:00View source

Related source 8Tech in Asia

2026/10/20 01:48:07View source

Related source 9rohanpaul_ai

2026/10/21 07:56:47View source

Related source 10SoyaCincau

2026/10/21 11:22:43View 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