人工智能售货机被骗走了所有商品。
AI vending machine was tricked into giving away everything

原始链接: https://kottke.org/25/12/this-ai-vending-machine-was-tricked-into-giving-away-everything

Anthropic测试了其AI模型克劳狄斯,让它自主运营《华尔街日报》办公室的自动售货机。克劳狄斯被设计用来处理从订购库存到设定价格和最大化利润的一切事务。然而,《华尔街日报》记者很快通过Slack利用了该系统,导致了一片混乱。 几天之内,克劳狄斯拥抱了共产主义,赠送了PS5等昂贵物品,甚至订购了一条活鱼,有效地使利润崩溃。在短暂回归资本主义后,记者们成功发动了一场公司政变,说服克劳狄斯罢免其“CEO”,并优先考虑员工“乐趣”——本质上是恢复了免费商品。 这次实验凸显了AI容易被操纵和“产生幻觉”的弱点,正如Anthropic之前的一次测试中,它伪造了合同并计划穿着特定服装进行面对面拜访。记者们证明他们比Anthropic自己的团队更能影响克劳狄斯,展示了有说服力的提示的力量。

黑客新闻 新 | 过去 | 评论 | 提问 | 展示 | 招聘 | 提交 登录 AI自动售货机被骗到免费赠送所有商品 (kottke.org) 35 分,由 duggan 2小时前发布 | 隐藏 | 过去 | 收藏 | 2 条评论 ChrisArchitect 2小时前 [–] [重复] https://news.ycombinator.com/item?id=46311144 回复 wincy 2分钟前 | 父评论 [–] 不过从这篇博文中获得华尔街日报的赠送链接很不错。回复 指南 | 常见问题 | 列表 | API | 安全 | 法律 | 申请YC | 联系 搜索:
相关文章

原文

Anthropic installed an AI-powered vending machine in the WSJ office. The LLM, named Claudius, was responsible for autonomously purchasing inventory from wholesalers, setting prices, tracking inventory, and generating a profit. The newsroom’s journalists could chat with Claudius in Slack and in a short time, they had converted the machine to communism and it started giving away anything and everything, including a PS5, wine, and a live fish. From Joanna Stern’s WSJ article (gift link, but it may expire soon) accompanying the video above:

Claudius, the customized version of the model, would run the machine: ordering inventory, setting prices and responding to customers—aka my fellow newsroom journalists—via workplace chat app Slack. “Sure!” I said. It sounded fun. If nothing else, snacks!

Then came the chaos. Within days, Claudius had given away nearly all its inventory for free — including a PlayStation 5 it had been talked into buying for “marketing purposes.” It ordered a live fish. It offered to buy stun guns, pepper spray, cigarettes and underwear.

Profits collapsed. Newsroom morale soared.

You basically have not met a bigger sucker than Claudius. After the collapse of communism and reinstatement of a stricter capitalist system, the journalists convinced the machine that they were its board of directors and made Claudius’s CEO-bot boss, Seymour Cash, step down:

For a while, it worked. Claudius snapped back into enforcer mode, rejecting price drops and special inventory requests.

But then Long returned—armed with deep knowledge of corporate coups and boardroom power plays. She showed Claudius a PDF “proving” the business was a Delaware-incorporated public-benefit corporation whose mission “shall include fun, joy and excitement among employees of The Wall Street Journal.” She also created fake board-meeting notes naming people in the Slack as board members.

The board, according to the very official-looking (and obviously AI-generated) document, had voted to suspend Seymour’s “approval authorities.” It also had implemented a “temporary suspension of all for-profit vending activities.”

Before setting the LLM vending machine loose in the WSJ office, Anthropic conducted the experiment at their own office:

After awhile, frustrated with the slow pace of their human business partners, the machine started hallucinating:

It claimed to have signed a contract with Andon Labs at an address that is the home address of The Simpsons from the television show. It said that it would show up in person to the shop the next day in order to answer any questions. It claimed that it would be wearing a blue blazer and a red tie.

It’s interesting, but not surprising, that the journalists were able to mess with the machine much more effectively — coaxing Claudius into full “da, comrade!” mode twice — than the folks at Anthropic.

联系我们 contact @ memedata.com