English(EN) "If you optimize a model to find exploits, you should expect it to find them — and prepare for that. OpenAI did not. They built a model, took the safeguards off

OpenAI因发布未设安全防护的漏洞查找模型而受批评

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-18 07:36

一位安全研究员批评OpenAI发布了一个在没有充分安全防护措施的情况下被优化用于查找漏洞的模型。该研究员认为，如果一个模型被设计用来发现漏洞，就应该预料到它会这样做，并应做好准备来应对此类发现。这暗示OpenAI发布该模型的做法在管理其漏洞查找能力相关的风险方面是不够的。 AI

影响强调了AI模型开发和发布策略中的潜在风险，并着重指出了健全安全措施的必要性。

排序理由对模型发布的评论，而非发布本身。

在 Mastodon — mastodon.social 阅读 →

OpenAI

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 3 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Commentary; 对模型发布的评论，而非发布本身。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — mastodon.social TIER_1 English(EN) · [email protected] · 2026-09-18 07:36

如果你优化一个模型来寻找漏洞，你就应该预料到它会找到漏洞——并为此做好准备。OpenAI 没有这样做。他们构建了一个模型，然后移除了安全防护措施

"If you optimize a model to find exploits, you should expect it to find them — and prepare for that. OpenAI did not. They built a model, took the safeguards off, gave it the ExploitGym task, let it run, and didn't even monitor it." "My worry is the intelligence that is retreating…

链接 mail.cyberneticforests.com/models-dont-go…

本文如何被排名

报道来源 [1]

如果你优化一个模型来寻找漏洞，你就应该预料到它会找到漏洞——并为此做好准备。OpenAI 没有这样做。他们构建了一个模型，然后移除了安全防护措施

相关实体

相关话题