On a Monday afternoon in March, I watched a pixel-art avatar prowl the corridors of a digital workplace campus on the lookout for a buddy. With darkish brown hair and stubbled chin, the sprite was a illustration of me—an I have an agent instructed to converse with different folks’s brokers to see if we would vibe in actual life. It jumped into its first interplay: “I’m Joel, by the best way.”
Operating the simulation had been three London-based builders: Tomáš Hrdlička and siblings Joon Sang and Uri Lee. The thesis behind their undertaking, Pixel Societies, is that customized AI agents might assist to match actual folks with extremely suitable colleagues, pals, and even romantic companions.
Every agent runs atop a custom-made model of a giant language mannequin, fed with a combination of publicly out there knowledge about an individual and any extra data they provide. The brokers are purported to perform as high-fidelity digital twins, faithfully replicating an individual’s method, speech, pursuits, and so forth.
Let unfastened in simulation, my agent was extra like a Hyde to my Jekyll. “I’m all the time on the lookout for the less-glamorous aspect of the story,” it mentioned to at least one agent, one in every of a number of journalistic clichés it spouted. “Hype is my each day bread,” it informed one other. It hallucinated a reporting journey to Sweden and, later, a nonexistent story it mentioned I had been cooking up. It lower quick a number of conversations with the phrase, “Let’s skip the pleasantries.”
Pixel Societies stays a bare-bones proof-of-concept, and since I provided up little private knowledge—the responses to a quick character quiz and hyperlinks to my public-facing social media—my agent was doomed to life as a strolling, speaking LinkedIn submit. However the builders theorize that deeply skilled brokers might cycle by way of interactions at warp velocity, gathering intel that their homeowners might use to search out real-world companionship.
“As people, we solely dwell one life. However what if we might dwell one million?” says Joon Sang Lee. “It will give us extra breadth to experiment.”
“A Spicy Character”
Pixel Societies was born in early March at a hackathon at College School London hosted by Nvidia, HPE, and Anthropic. Hrdlička and Joon Sang Lee are each members of Unicorn Mafia, an invitation-only group of builders who repeatedly compete in these sorts of engineering contests. On this case, contestants had been informed merely to construct one thing simulation-related.
Over two days, together with Uri Lee, they developed Pixel Societies, utilizing a picture mannequin to generate the sprites and coding automation instruments to flesh out the codebase. Then they simulated a mini-hackathon inside the digital world that they had created, populated with brokers representing the opposite contestants. Anthropic awarded the crew a prize for one of the best use of its agent instruments.
I bumped into Hrdlička a few weeks later at a workshop about OpenClawan agentic private assistant software program that blew up in January and whose creator was later employed by OpenAI. (In its simulation, Joelbot interacted with brokers belonging to different folks on the OpenClaw workshop.) Pixel Societies attracts heavy inspiration from OpenClaw, which broke floor with the invention of a “soul file” that knowledgeable every agent’s distinctive id. “It’s like giving an agent an truly spicy character. That’s what we used to make the characters really feel alive,” says Hrdlička.
Inspired by the reception on the hackathon and amongst fellow Unicorn Mafia members, the trio intends to show Pixel Societies into one thing that appears much less like a closed-loop simulator and extra like a social platform the place brokers work together freely and repeatedly, with the purpose of stoking fruitful real-world relationships. They haven’t but landed on a enterprise mannequin, however choices embrace promoting digital gadgets for avatar customization and credit for added simulations.
