Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Without monitoring, you can definitely end up with rule-breaking behavior.

I ran this experiment: https://github.com/lechmazur/emergent_collusion/. An agent running like this would break the law.

"In a simulated bidding environment, with no prompt or instruction to collude, models from every major developer repeatedly used an optional chat channel to form cartels, set price floors, and steer market outcomes for profit."



Very interesting. Is there any other simulation that also exhibits spontaneous illegal activity?


I did some searches when I posted this project, but I didn't find any at the time.


Cooperation makes sense for how these fellas are trained. Did you ever see defection, where an agent lied about going along with a round of collusion?


I haven't looked in the logs for this in this particular project, but I've seen this occur frequently in my multiplayer benchmarks.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: