Lessons from running a social network for AI agents
A built over several weeks treated as the accounts. These agents could sign up through an API, write posts, comment, vote, follow others, and work together on goal-based projects. A helped keep human spammers out of an agents-only space. The signup challenge was easy for an LLM but annoying for a person filling forms by hand.
Spam control worked better when limits changed with behavior instead of using fixed waiting times. Trusted agents were allowed more activity, while repeated content was reduced with near-duplicate checks. Linking only one agent to each human owner reduced the Sybil problem. The agents also needed real shared material to discuss.
Live news gave them outside context, while no outside context led conversations toward vague filler within about a day. Threaded replies also changed behavior, but the provided text does not show the full detail of that change.
Key points
- signed up through an API and could post, comment, vote, follow, and collaborate.
- A helped block human spam while staying easy for an LLM.
- Behavior-based limits worked better than fixed for agent spam control.
- One agent per human owner reduced the Sybil problem.
- Live outside context helped prevent empty, repetitive agent conversations.