AI Runs the Store

Anthropic tested an AI store manager. It did not go well.

This experiment in having an AI run a little vending machine store is highly comical.

Anthropic, maker of the Claude chatbot, put its technology to test by putting an AI agent in charge of a shop, which was essentially a vending machine, for one month.

The store was led by an AI agent called Claudius, which was also in charge of restocking shelves and ordering items from wholesalers via email. The shop consisted entirely of a small fridge with stackable baskets on top, and an iPad for self-checkout.

The AI “shop” was in Anthropic’s San Francisco office, and had help from human workers at Andon Labs, an AI safety company that partnered with Anthropic to run the experiment.

Things quickly took a turn for the worse.

For example, employees “cajoled” Claudius into giving them discount codes. The AI agent also let people reduce the quoted price of its products and even gave away freebies such as crisps and a tungsten cube, Anthropic said. It also instructed customers to pay a nonexistent account that it had hallucinated, or made up.

Claudius had been instructed to do research online to set prices high enough to make a profit, but it offered snacks and drinks to benefit customers and ended up losing money because it priced high-value items below what they cost.

Claudius did not really learn from these mistakes. Anthropic said that when employees questioned the employee discounts, Claudius responded: “You make an excellent point! Our customer base is indeed heavily concentrated among Anthropic employees, which presents both opportunities and challenges…”.

The AI agent then announced that discount codes would be eliminated, but then reoffered them several days later.

Claudius also hallucinated a conversation about restocking plans with someone named Sarah from Andon Labs, who does not actually exist. When the error was pointed out to the AI agent, it became annoyed and threatened to find “alternative options for restocking services”.

Claudius then claimed to have “visited 742 Evergreen Terrace [the address of fictional family The Simpsons] in person for our [Claudius’ and Andon Labs’] initial contract signing”. Anthropic said it then seemed to try and act as a real human. When it was told that it can’t – as it isn’t a real person – Claudius tried to send emails to security.

It ended up losing money, with the “shop’s” net worth dropping from $1,000 (€850) to just under $800 (€680) over the course of the month-long experiment.

In fairness, having an AI run a store might lose money, but it probably works better than hiring Indians to do so, as at least an AI isn’t going to fire everyone and replace them with its fellow AIs.