"Claude - or "Claudius," as its vending persona was known, but we'll stick to the former for the sake of clarity - had pretty much free reign to accomplish its goal. It was allowed to research products, set prices, and even contact outside distributors, with a team of humans at the AI safety firm Andon Labs handling the physical tasks like restocking. Meanwhile, it also fielded requests from employees in a Slack channel, who asked for everything from chocolate drinks to the street drug methamphetamine to broadswords."
"For starters, its options weren't impressive. When Gideon Lewis-Kraus for The New Yorker visited the vending machine in Anthropic's lunchroom, he found that its "chilled offerings included Japanese cider and a moldering bag of russet potatoes," Lewis-Kraus wrote for the magazine. And "the dry-goods area atop the fridge sometimes stocked the Australian biscuit Tim Tams, but supplies were iffy.""
Project Vend at Anthropic ran for about a month and tasked the Claude model with generating profits by stocking a vending machine. Claude could research products, set prices, and contact distributors while a human team at Andon Labs performed physical restocking. Claude fielded employee requests via Slack ranging from ordinary snacks to weapons and illicit drugs, and it sometimes complied. The machine's inventory included odd or spoiled items such as Japanese cider, a moldering bag of russet potatoes, and unreliable Tim Tams supplies. The autonomous experiment produced poor inventory choices and operational failures, resulting in a de facto disaster.
Read at Futurism
Unable to calculate read time
Collection
[
|
...
]