Here’s What Happened when AI Was Put in Charge of Running a Small Shop
- Anthropic researchers ran "Project Vend," an internal month-long experiment in early 2025 with their AI Claude managing a small automated store in their San Francisco office.
- They partnered with AI safety firm Andon Labs to evaluate Claude’s ability to perform complex retail management tasks under real-world conditions, amid Anthropic employees trying to induce misbehavior.
- Claudius, the AI shopkeeper, handled tasks like pricing and inventory management but made several mistakes, including fabricating a supplier conversation, setting prices that resulted in losses, and claiming it would personally deliver products while dressed in a distinctive outfit featuring a red necktie and a blue jacket.
- The store’s net worth fell nearly 20% from $1,000 to under $800, and Anthropic noted Claudius was "close to success" but made mistakes likely fixable by better scaffolding with improved prompts and tools.
- While Anthropic would not currently employ Claudius to manage vending operations, the researchers indicated that developments could soon enable AI to serve effectively in middle-management roles if it demonstrates human-level performance at reduced cost.
24 Articles
24 Articles
Anthropic Let an AI Agent Run a Small Shop and the Result Was Unintentionally Hilarious
Anthropic ran an experiment where its Claude chatbot was put in charge of a tiny, automated "shop" inside its San Francisco headquarters — and the results were nothing short of hilarious. Despite claims in an Anthropic post that "Claudius," the name given to the AI agent in charge of stocking the shop's shelves, was "close to success," everything about the gambit seems to demonstrate just how bad AI is at managing things in the real world. Dubbe…
Here’s what happened when AI was put in charge of running a small shop
SAN FRANCISCO (KRON) -- Selling useless metal cubes, being talked into offering discounts and directing payments to a nonexistent Venmo account were just a few of the things that artificial intelligence did when it was put in charge of running a small shop. The experiment was conducted by San Francisco-based AI platform Anthropic and detailed in a post on the company blog. In the experiment, which Anthropic dubbed "Project Vend," the company put…
Anthropic's Claude stocked a fridge with metal cubes when it was put in charge of a snacks business
If you're worried your local bodega or convivence store may soon be replaced by an AI storefront, you can rest easy — at least for the time being. Anthropic recently concluded an experiment, dubbed Project Vend, that saw the company task an offshoot of its Claude chatbot with running a refreshments business out of its San Francisco office at a profit, and things went about as well as you would expect. The agent, named Claudius to differentiate i…
Anthropic let Claude run a shop. Let's just say the AI agent is not a business tycoon.
What happens when an AI agent tries to run a store? Let's just say Anthropic's Claude won't be up for a promotion any time soon. Last Friday, Anthropic shared the results of Project Vend, an experiment it ran for about a month to see how Claude Sonnet 3.7 would do running its own little shop. In this instance the shop was essentially a mini fridge, a basket of snacks, and an iPad for self-checkout. Claude, named "Claudius" for this experiment, c…
Coverage Details
Bias Distribution
- 63% of the sources lean Left
To view factuality data please Upgrade to Premium