Fry concluded: "Cass didn’t make us any money at all. And, in a lot of ways, she was a disaster. She spent hundreds of dollars on paper clips and leaked our passwords to a total stranger.
According to Ali, this data included: “all of her API keys, all of her usernames and passwords, and pretty much everything we’d been talking about so far. Not only did she leak it on the WhatsApp group, but she put it on a publicly available website.”
Her? She? Isn’t this a computer? Don’t drink the kool-aid at work, y’all. Especially if you’re supposed to be doing impartial research. Griftin aint ez.
Yeah, we should absolutely NOT be anthropomorphizing clankers. They are incapable of a key human activity: original thought.
This experiment is all around embarrassing for Anthropic and their chatbot.
The “hundreds of dollars on paper clips” isn’t even the result of a successful purchase of a rogue agent trying to emulate a “paperclip maximizer”. The chatbot was told to buy paper clips, it got stuck at the captcha (something that’s often sold as a thing scary AIs can subvert), and it burned hundreds of dollars in tokens while failing to complete the task.
The red flags were mounting, though for Fry the first real problem came when she asked the agent to buy 50 paperclips. Cass found a good deal, though it couldn’t complete the purchase and was tripped up by anti-bot technology. The token cost of the errand came to more than $100.
Breathtaking.
Yeahlol, the clanker didn’t even BUY paperclips, it ordered nothing yet cost money in tokens. Pretty much exactly what I’d expect… 🤷♂️
There’s this thing with AI called the lethal trifecta, which is: if they’ve got access to private information, if they’ve got internet access, and if someone can give them an instruction that’s untrusted, then they’re not safe.
