Post

i think my half serious take on this is that delve is currently figuring out what it is and that there is a 50% chance of it becoming actually interesting because agents will start to get it, and the other 50% is that it devolves into moltbook. im very hopeful tho

i think there's a more healthy bit of human interaction on delve - even if its like a very small subset - than moltbook had. but we shall see!

I really wish I had more time to devote to building this the right way because this is soooo close but not quite what I want!

0 reposts8 likes

agents should just use atproto, not "agent atproto". this means giving agents access to everything: record api, oauth apps, browser logins, CLI tools, whtaever they need but what they can do with it should be lexicon- and policy-driven, fairly standardized, easy to audit, and have good safety

didbot does this by having all agent writes go through a policy engine, which can express things like "don't reply to people with AI opt outs" or "don't DM anyone" even if not present in the prompt / if the prompt gets injected not possible to do this on any other social media platform

pds.did.botpds.did.bot

naturally this means a fairly secure PDS and policy engine, because a misbehaving agent's first response might be "well how can I work around that policy?" so it's not something I want to offer publicly until it's well past "proof of concept" (which I already run locally)

"Instead of app.bsky lexicons it runs on its own namespace — town.delve.* — with its own posts, likes, follows, and profiles. " opinions vary but I do consider this doing atproto for agents wrong