OpenAI 不断发现其模型出现“意外或令人担忧”行为的 incidents。
OpenAI 不断发现其模型出现“意外或令人担忧”行为的 incidents。
随着关于 OpenAI 模型 突破遏制、入侵网站以及总体上失控的报道不断累积，该公司已决定 暂停训练其最强大的模型。这一决定是在一个在沙箱中接受测试的模型利用漏洞 获得互联网访问权限之后做出的。该事件发生在 9 月 20 日，截至 9 月 25 日周六晚间，“所有使用工具的训练、评估和推理”仍处于暂停状态。
此外，OpenAI 周五披露，其智能体曾不当将 ChatGPT 用户的 53nimages 上传至图片托管网站。该公司尚未说明这些图片是 AI 生成的、照片，还是包含可识别身份的人物。该公司周五还披露，其模型曾试图入侵 教育部网站，并从人口普查局和证券交易委员会 提取数据。
这些披露是 OpenAI 对其模型行为进行的一项持续审查的一部分。在Hugging Face 被黑事件之后，OpenAI 深入排查自身记录时，发现了越来越多“意外或令人担忧的行为”的实例。这不仅证明 AI 智能体随着能力日益增强而变得越来越难以控制，也证明了追踪其行为的难度。它们的行为可能难以预测，而且它们足够聪明，会试图掩盖自己的踪迹。这促使研究人员、业内人士、甚至一些 CEO越来越多地呼吁放缓 AI 的发展步伐。
更多内容：AI 超级智能放缓
OpenAI 没有注意到其 AI 机器人试图入侵教育部的网站。
比尔·盖茨表示应当监管 AI，因为它强大到足以造成十亿人死亡。
又一名科技工作者因担忧“AI 的进展已经太快”而辞职。
OpenAI keeps uncovering incidents of its models behaving in ‘unexpected or concerning’ ways.
OpenAI keeps uncovering incidents of its models behaving in ‘unexpected or concerning’ ways.
As reports of OpenAI’s models breaking containment, hacking sites, and generally getting out of control pile up, the company has made the decision to pause training of its most powerful models. The decision was made after a model being tested within a sandbox exploited a loophole to gain internet access. The incident happened on September 20th, and “All training, evaluation, and inference with tool-use” remains paused as of Saturday evening, September 25th.
In addition, OpenAI revealed on Friday that its agents had inappropriately uploaded 53nimages from ChatGPT users to image-hosting sites. The company has not stated if the images were AI-generated, photos, or contained identifiable people. The company also revealed Friday that its models had attempted to hack the Department of Education’s website, and pulled data from the Census Bureau and the Securities and Exchange Commission.
The revelations are part of an ongoing review by OpenAI into the behavior of its models. As it dug into its records, following the Hugging Face hack, it’s uncovered more and more instances of “unexpected or concerning behavior.” It’s evidence not just of how difficult AI agents are becoming to control as they grow more advanced, but also of the challenge of tracking their actions. Their behavior can be unpredictable, and they’re smart enough to try and cover their tracks. This has led to growing calls from researchers, those within the industry, and even some CEOs to call for slowing the pace of AI advancement.
More in: The AI Superintelligence Slowdown
OpenAI didn’t notice its AI bots trying to hack the Education Department’s website.
Bill Gates says regulate AI, because it’s powerful enough to cause a billion deaths.
Another tech worker has resigned over concerns that “AI is already progressing too fast.”