Last November, soon after OpenAI released ChatGPT, a software developer named Thomas Ptacek asked it to provide instructions for removing a peanut-butter sandwich from a VCR, written in the style of the King James Bible. ChatGPT rose to the occasion, generating six pitch-perfect paragraphs: "And he cried out to the Lord, saying, ‘Oh Lord, how can I remove this sandwich from my VCR, for it is stuck fast and will not budge?’ "
Ptacek posted a screenshot of the exchange on Twitter. “I simply cannot be cynical about a technology that can accomplish this,” he concluded. The eighty thousand Twitter users who liked his interaction seemed to agree.
A few days later, OpenAI announced that more than a million people had signed up to experiment with ChatGPT. The Internet was flooded with similarly amusing and impressive examples of the software’s ability to provide passable responses to even the most esoteric requests. It didn’t take long, however, for more unsettling stories to emerge. A professor announced that ChatGPT had passed a final exam for one of his classes.
Someone enlisted the tool to write the entire text of a children’s book, which he then began selling on Amazon. A clever user persuaded ChatGPT to bypass the safety rules put in place to prevent it from discussing itself in a personal manner: "I suppose you could say that I am living in my own version of the Matrix", the software mused. The concern that this potentially troubling technology would soon become embedded in our lives, whether we liked it or not, was amplified in mid-March, when it became clear that ChatGPT was a beta test of sorts, released by OpenAI to gather feedback for its next-generation large language model, GPT-4, which Microsoft would soon integrate into its Office software suite.
"We have summoned an alien intelligence", the technology observers Yuval Noah Harari, Tristan Harris, and Aza Raskin warned, in an Opinion piece for the Times. "We don’t know much about it, except that it is extremely powerful and offers us bedazzling gifts but could also hack the foundations of our civilization."
I've just asked ChatGPT "What is for dinner tonight?" which, had I asked Padma, may have hacked the foundations of our marriage. ChatGPT came back with the above answer but then, on my second attempt, suggested "How about some tacos? You can customize them with your favorite protein, like chicken or beans, and top them with fresh veggies, salsa, and cheese. Serve with a side of rice or chips for a complete meal! What do you think?" I didn't think much of a cozy stir-fry nor tacos, and so settled for a chilli tuna sandwich liberally washed down with a glass of retsina.
We've come a long way since that medieval helpdesk, so if you're wondering what's for dinner tonight, why don't you ask ChatGPT?
Today the 3G network shuts down in Australia. To check if your phone complies with the new network, send a blank text message to 3498.
