Tim Burd

ChatGPT is so last month 😴 🔥 Stanford/Google researchers just dropped some mindblowing new research on generative agents, and it's like they brought Westworld to life. 🤖 Here's what you should know⤵️⤵️⤵️ Using a simulation video game they created, researchers made 25 characters that could: Communicate with others and their environment 💬 Memorize and recall what they did and observed 🧠 Reflect on those observations 🤔 Form plans for each day 📅 Then, they gave them some memories: An identity (name, occupation, priorities) 📝 Information about/relationships with other characters 💑 Some intention about how to spend their day 💭 Then, they pressed play. ▶️ With just this information alone, the characters acted much like humans do: They shared information with each other 🗣️ Example: Isabella starts the day with a plan to host a Valentine's Day party. She spreads the word, and by the end of the simulation, 12 characters know about the party 🥳 Much like humans, 7 of them flaked - 3 of them had "other plans" and the other 4 just didn't show. 😒 They form new relationships and remember them 💞 Example: Sam and Latoya don't know each other at the start. They meet at a park, and Latoya says she's working on a photography project... 📸 When Sam and Latoya meet again later, Sam says: "Hi, Latoya. How is your project going?" 📷 They coordinate with each other 🤝 Example: Researchers gave Isabella (the v-day party host) and Maria two pieces of info: Isabella: You will throw a party 🎉 Maria: You have a crush on Klaus 💘 Without any further instruction, Isabella invites people to the party, decorates the venue, and asks Maria for help. Meanwhile, Maria jumps at the opportunity to get closer to Klaus by inviting him along as well. 😍 This is fascinating new research 📚 We've officially moved past 'AI models can write blog posts for me' and into "How much can AI models act like humans?" territory. 🤖➡️👫 We're moving fast 💨. Paper - arxiv.org/abs/2304.03442 Credit - @nonmayorpete