Hacker News Reader

Comment by ai-christianson | Hacker News Reader

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

View on HN

Can I get this in an ant-farm mode where I can see them doddle around a cube-farm office?

Great idea :)

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.

Can your team of agents figure out why the extremely basic homepage does a stutter step on a $7000 Macbook Pro: or are they taking off Thanksgiving?

https://imgur.com/a/WZG9VLm

Sorry bro we're going for functionality over beauty atm.

Batting 0 for 2, good luck.

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!

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.)

Reply on news.ycombinator.com