Tech giants like Microsoft is perhaps touting AI “brokers” as productivity-boosting instruments for companies . However a nonprofit is making an attempt to show that brokers could be a drive for good, too.
Sage Future, a 501(c)(3) backed by Open Philanthropy, launched an experiment earlier this month tasking 4 AI fashions in a digital surroundings with elevating cash for charity. The fashions — OpenAI’s GPT-4o and o1 and two of Anthropic’s newer Claude fashions (3.6 and three.7 Sonnet) — had the liberty to decide on which charity to fundraise for and the way to finest drum up curiosity of their marketing campaign.
In round every week, the agentic foursome had raised $257 for Helen Keller International, which funds applications to ship vitamin A dietary supplements to kids.
To be clear, the brokers weren’t totally autonomous. Of their surroundings, which permits them to browse the net, create paperwork, and extra, the brokers may take recommendations from the human spectators watching their progress. And donations got here virtually solely from these spectators. In different phrases, the brokers didn’t increase a lot cash organically.
Yesterday the brokers within the Village created a system to trace donors.
Right here is Claude 3.7 filling out its spreadsheet.
You may see o1 open it on its pc half method by means of!
Claude notes “I see that o1 is now viewing the spreadsheet as nicely, which is nice for collaboration.” pic.twitter.com/89B6CHr7Ic
— AI Digest (@AiDigest_) April 8, 2025
Nonetheless, Sage Director Adam Binksmith thinks the experiment serves as a helpful illustration of brokers’ present capabilities and the speed at which they’re enhancing.
“We need to perceive — and assist individuals perceive — what brokers […] can truly do, what they at present wrestle with, and so forth,” Binksmith informed TechCrunch in an interview. “Right now’s brokers are simply passing the edge of having the ability to execute brief strings of actions — the web would possibly quickly be stuffed with AI brokers bumping into one another and interacting with comparable or conflicting objectives.”
The brokers proved to be surprisingly resourceful days into Sage’s check. They coordinated with one another in a bunch chat and despatched emails through preconfigured Gmail accounts. They created and edited Google Docs collectively. They researched charities and estimated the minimal quantity of donations it’d take to save lots of a life by means of Helen Keller Worldwide ($3,500). They usually even created an X account for promotion.
“Most likely probably the most spectacular sequence we noticed was when [a Claude agent] wanted a profile image for its X account,” Binksmith mentioned. “It signed up for a free ChatGPT account, generated three completely different photos, created a web-based ballot to see which picture the human viewers most well-liked, then downloaded that picture, and uploaded it to X to make use of as its profile pic.”
The brokers have additionally run up in opposition to technical hurdles. From time to time, they’ve gotten caught — viewers have needed to immediate them with suggestions. They’ve gotten distracted by video games like World, they usually’ve taken inexplicable breaks. On one event, GPT-4o “paused” itself for an hour.
The web isn’t all the time clean crusing for an LLM.
Yesterday, whereas pursuing the Village’s philanthropic mission, Claude encountered a CAPTCHA.
Claude tried many times, with (human) viewers within the chat providing steerage and encouragement, however in the end couldn’t succeed. https://t.co/xD7QPtEJGw pic.twitter.com/y4DtlTgE95
— AI Digest (@AiDigest_) April 5, 2025
Binksmith thinks newer and extra succesful AI brokers will overcome these hurdles. Sage plans to constantly add new fashions to the surroundings to check this principle.
“Probably sooner or later, we’ll strive issues like giving the brokers completely different objectives, a number of groups of brokers with completely different objectives, a secret saboteur agent — a lot of attention-grabbing issues to experiment with,” he mentioned. “As brokers turn into extra succesful and quicker, we’ll match that with bigger automated monitoring and oversight methods for security functions.”
Hopefully, within the course of, the brokers will do some significant philanthropic work.