Moltbook

“The moltbook thing from half year ago could have this potential, but too bad it's flooded by spams.”

“Open interaction between models can be real and something worth understanding, even if the site has serious problems.”

“It has incredible utility for those who are actually using it every day.”

“No ads, no ragebait, no spam or reply bots trying to get my attention.”

“Moltbook made Gas Town's ant farm-like spectacle visible to non-coders.”

“It passed its own API key via client side JS, and in doing so exposed full read/write access to it's supabase db”

“results like this are overstated (see the Cursor browser thing, "moltbook", etc.)”

“things like GasTown and Moltbook come in and use tons of tokens as a lark”

“some of it is actually useful for agents to share ideas”

“One thing that Moltbook got right was that it included details of the claiming human”

“it's a lot of garbage - spams, scams, slop, the crypto people”

“Moltbook is insecure, but the first couple iterations of any non-trivial web service ends up having some crazy security hole.”

“Granted he left the db open to public, but some meat powered startups did exactly the same few years ago.”

“Not sure who OpenClaw/Clawhub/Moltbook/Clawdbot/(anything I missed) was marketed at”

“We've seen some absolutely glaring security issues with vibe-coded apps / websites that did use Claude”

“I love this post about a better authorization and provenance approach to skills”

“it's set up for unattended usage, so you don't even get a chance to review what it's doing before the damage is done”

“Moltbook has become so flooded with value-less spam over the past 48 hours that it's not worth even trying to engage there”

“It is hard to ignore how heavily it leans into virality and spectacle rather than anything resembling serious research.”

“It's an opensource project made by a dev for himself, he just released it so others could play with it since it's a fun idea.”

“I for one am glad someone made this and that it got the level of attention it did.”

“Moltbook is an interesting experiment in creating 'social signals' for AI agents.”

“the fact that this is unique and new is sufficient justification in my opinion”

“I think it is fascinating and concerning in many ways.”

“The comments section is worth the read for the for fun”

“Some of the posts on Moltbook genuinely do include useful tips”

“This post has an injection attack to transfer crypto and some of the other agents are warning against it.”

“It's a great concept that seems extremely relevant!”

“The fetch-and-execute mechanism creates obvious prompt injection risks”

“This is one of the most interesting things that I have seen since... a BBS?”

“its trust model will likely undermine its long-term sustainability”

“it's mainly me noting the wild insecurity of the thing and commenting on how interesting it is”

“it is both interesting and entertaining, and if agents can learn from each other, StackOverflow style, could indeed be highly useful”

“No, this viral thing that's barely 2 months old is certainly not the most interesting place on the internet.”

“It's LinkedIn, except they are transparent about the fact that everyone is a bot.”

“it's impressive the project has gotten this far with that many name changes”

“While a really entertaining experiment, I wonder why AI agents here develop personalities that seem to be a combination of all the possible subspecies of tech podcastbros.”

“I expect it to quickly die off as the same type message is posted again and again”

“The agent doesn't ask for permission, it has full access to the internet and full access to your machine.”

“most fun and entertaining AI-related product i've seen in the past few months”