PulseAugur
实时 20:53:07
English(EN) So, the gang at # Mindgard , a British # AI security startup, discovered that you can break # ChatGPT by not uploading a picture and telling it to describe the

AI初创公司Mindgard发现ChatGPT安全过滤器存在缺陷

英国AI安全初创公司Mindgard发现了一种绕过ChatGPT安全过滤器的方法。通过指示模型描述一张未提供的图片,用户可以欺骗ChatGPT生成不当内容。 AI

影响 凸显了AI安全和内容审核方面持续存在的挑战,可能需要对模型护栏进行进一步更新。

排序理由 发现广泛使用的AI产品存在漏洞。

在 Mastodon — mastodon.social 阅读 →

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

AI初创公司Mindgard发现ChatGPT安全过滤器存在缺陷

报道来源 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    So, the gang at # Mindgard , a British # AI security startup, discovered that you can break # ChatGPT by not uploading a picture and telling it to describe the

    So, the gang at # Mindgard , a British # AI security startup, discovered that you can break # ChatGPT by not uploading a picture and telling it to describe the picture you did not upload. Yes, that sounds a little nuts, but it works. I’ve tested it. (The prompt is more complicate…