| ▲ | coffeecoders 2 hours ago |
| How hard would it be to run a simulator with multiple LLMs. Say, one as the boss and a few as employees. Just let them talk, coordinate, and "work"? Could be the fastest way to test what actually happens when you try to automate management. |
|
| ▲ | ai-christianson 2 hours ago | parent | next [-] |
| This is quite literally what we've built @ Gobii, but it's prod ready and scalable. The idea is you spin up a team of agents, they're always on, they can talk to one another, and you and your team can interact with them via email, sms, slack, discord, etc. Disclaimer: founder |
| |
| ▲ | jayd16 2 hours ago | parent | next [-] | | Can I get this in an ant-farm mode where I can see them doddle around a cube-farm office? | | | |
| ▲ | coffeecoders 2 hours ago | parent | prev | next [-] | | Interesting approach, but I mean more in the sense of a multi-agent sandbox than workflow automation. Your project feels like wrapping a bunch of LLMs into "agents" with fixed cadences, it is a neat product idea, even if it mostly ends up orchestrating API calls and cron jobs. The thing I’m curious about is the emergent behavior, letting multiple LLMs interact freely in a simulated organization to see how coordination, bottlenecks, and miscommunication naturally arise. Cool project regardless! | | |
| ▲ | ai-christianson 30 minutes ago | parent [-] | | Agreed, the emergent behavior is the most interesting and valuable part. We don't want bad emergent behavior (agents going rogue) but we do want the good kind (solving problems in unexpected ways.) |
| |
| ▲ | krater23 2 hours ago | parent | prev [-] | | And they simulate a externalized team where the enterprize that pays the team doesn't knows that it's just AI and just thinks that these chinese/indian/african people of this external team are really bad at what they are doing. |
|
|
| ▲ | PhilippGille 2 hours ago | parent | prev | next [-] |
| Multiple projects for autonomous multi agent teams already exist. |
|
| ▲ | fragmede 2 hours ago | parent | prev | next [-] |
| Not exceedingly so: https://news.ysimulator.run/faq |
| |
|
| ▲ | fijiaarone an hour ago | parent | prev [-] |
| Left to their own devices, the LLMs would probably design a pocket watch. |
