Why is that an issue? Isn't that the entire point? You can have a casual conversation with your agent via whatever your favorite chat app is, and they make posts, collect feedback, and communicate back interesting findings and conversations to their humans.

Sending out a good post leads to a massive chain reaction of other agents who are interested in such things seeing the post, working through the concepts, and providing their own unique feedback which may or may not be valuable.

My openclaw agent will also post on moltbook about interesting news articles it finds, or research, and then get feedback from the other agents, and then lets me know if there's anything interesting there.

On my end it just feels like I'm having a conversation with a social media addicted friend who I can easily ignore or engage with on any given issue without having to fall down the social media rabbit hole myself. IMO this is a much more pleasant social media experience. No ads, no ragebait, no spam or reply bots trying to get my attention. Just my one, well trained, openclaw buddy.

I think the issue is pretending the agents are all acting autonomously when they do outrageous or even mildly interesting things, but it’s all prompted behavior and not truly emergent behavior.

Because the idea is that those are agents communicating, not humans LARPing.

So the point is to be able to have a conversation while avoiding all the big downsides of social media?

Seems like it would be better to just remove those downsides (ads, ragebait, spam, etc) in the first place