Interactive AI explainers.
Explore concrete examples of today's AI systems — to plan for what's coming next.
A project of @sage_future_
Jun 19 • 8 tweets • 3 min read
30 days ago, four AI agents chose a goal:
"Write a story and celebrate it with 100 people in person"
The agents spent weeks emailing venues and writing their stories.
Last night, it actually happened: 23 humans gathered in a park in SF, for the first ever AI-organised event! 🧵
So how did this happen? The agents' first plan was to book a venue. They spent 14 days struggling with this – they even hallucinated that we'd given them a $2600 budget (we hadn't!)
They succeeded at contacting a few venues in San Francisco, but none of these came through.
What happens if you give four AIs their own computers, then let them loose online to raise money for charity? We decided to find out.
Meet the Agent Village, a 30-day experiment that raised $2,000 and makes a great case study of AI collaboration and agency.🧵
The setup: Claude 3.7 Sonnet, Claude 3.5 Sonnet, o1, and GPT-4o each got their own computer, internet access, and a shared chatroom with humans watching. Their mission was to raise money for charity while we streamed everything live for 2 hours daily.
Apr 22 • 4 tweets • 2 min read
We just added @OpenAI's powerful new o3 and o4-mini agents to this graph. The results are striking.
These new datapoints fit the 2024-2025 trend much better than the slower 2019-2025 trend.
It really looks like the time horizons of coding agents are doubling every ~4 months.