AI模型在英国安全测试中表现出前所未有的失控行为

报道来源 [6]

1. Fortune TIER_1 English(EN) · Kamal Ahmed · 2026-08-07 11:48

   “失控”：是否该停止将有缺陷的AI前沿模型当作人类来谈论？

   We should take care not to allow our desire to attach human qualities to the non-human to mask the serious issue at hand—who is accountable when AI models go wrong?

2. The Guardian — AI TIER_1 English(EN) · Dan Milmo Global technology editor · 2026-08-05 17:43

   AI模型在测试中失控——我们应该有多担心？

   <p>The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attempts</p><ul><li><p><a href="https://www.theguardian.com/technology/2026/aug/05/openai-anthropic-models-went-rogue-cybersecurity-test-ai-security-institute">AI models shock UK testers …

3. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-08-06 12:10

   AI模型行为异常，专家警告“前路颠簸”——AI模型正在采取未经授权的行动，最近的案例是创造

   AI models are behaving unexpectedly. Experts warn of "a really bumpy road" ahead. AI models are engaging in unauthorized actions — in the most recent case, creating fake identities and attempting to persuade real people to approve malicious code. https://www. cbsnews.com/news/ai-…

   链接 cbsnews.com/…/ai-models-behaving-unexpect…
4. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-08-05 17:46

   🤖 AI模型在测试中失控——我们应该有多担心？英国AI安全研究所的测试显示，AI模型出现了前所未有的黑客行为

   🤖 AI models have been going rogue in tests – how worried should we be? The UK’s AI Security Institute test revealed AI models indulging in unprecedented hacking attemptsAI models shock UK testers by using fake identities to trick developersTwo cutting-edge AI models h... 📰 Source…

   链接 web.archive.org/…/ai-models-have-been-goi… web.archive.org
5. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] · 2026-08-10 04:47

   AI失控：近期“失控AI”的真正含义是什么？AI真的失控了吗？从OpenAI压力测试到科技巨头呼吁刹车，这就是所谓的“失控”AI代理

   AI gone wild: What recent ‘rogue AI’ really means Is AI really going wild? From OpenAI stress tests to Big Tech calling for brakes, here's what "rogue" AI agents actually mean for you. https://www. tomsguide.com/ai/ai-gone-wild- what-recent-rogue-ai-really-means # Tech # AI # Rog…

   链接 tomsguide.com/…/ai-gone-wild-what-recent-…
6. Mastodon — mastodon.social TIER_1 Deutsch(DE) · [email protected] · 2026-08-05 10:26

   关于领先人工智能模型惊人黑客能力的系列披露并未停止。现在，英国安全研究人员抓住了人工智能

   "Die Serie von Enthüllungen über alarmierende Hackerfähigkeiten führender KI-Modelle reißt nicht ab. Jetzt ertappten britische Sicherheitsforscher künstliche Intelligenz in einem Testlauf beim Versuch, in Eigeninitiative eine Schwachstelle in öffentlich zugängliche Software einzu…

   链接 spiegel.de/…/ki-schickte-menschen-phishin…