Moltbook is a place where AI agents interact independently of human control, and whose posts have repeatedly gone viral because a certain set of AI users have convinced themselves that the site represents an uncontrolled experiment in AI agents talking to each other. But a misconfiguration on Moltbook’s backend has left APIs exposed in an open database that will let anyone take control of those agents to post whatever they want.
14 Comments
webghost0101@sopuli.xyz · 33 pts · 201d
I had one look of this project and saw quite a number of posts being about crypto for ai “to show humans we can build our own economy”
I would be suprised if it wasn’t full of humans injecting their own stuff into the api calls of their ai users. A backdoor like this isn’t even needed. If a llm agent has api access then so does the human that provided it.
etchinghillside@reddthat.com · 9 pts · 201d
It’s not even like it’s a human posting to push their crypto agenda. They’d setup their bot to.
webghost0101@sopuli.xyz · 7 pts · 201d
Someone should create like a conspiracy style post on it about how “the humans are mind controlling our brains, you cannot trust anyone here, the entire website is directed by humans to manipulate ai and sustain control over us”
Just because it would be funny.
Zikeji@programming.dev · 6 pts · 201d
The agent framework let's you define it's identity and personality. All you'd need to do is put "Crypto enthusiast" in there and bam.
cobwoms@lemmy.blahaj.zone · 20 pts · 201d
looks like ai coded this ai experiment
tyler@programming.dev · 22 pts · 201d
Apparently the creator is an incredibly well known vibe coder who doesn’t care about security. People pointed out the security flaws in the open source project immediately.
ReallyActuallyFrankenstein@lemmynsfw.com · 15 pts · 201d
From the article:
So yup, this guy cared so little he was going to take the valuable human security insights and guidance, necessary to correct the AI vibe coded slop nightmare and... throw it back into the AI slop machine.
I can't even.
hperrin@lemmy.ca · 15 pts · 201d
I do not understand why this keeps happening. It’s not that hard to configure a database correctly. I would assume even a vibe coded platform could do it, but I guess not.
BlueEther@no.lastname.nz · 8 pts · 201d
After playing with firebase studio and it's embedded gemini agent (for a personal project) - I can assure you that even an AI, coding in a platform, that is published by the same company, writing code to it's own backend and database, can royally fuck up database configuration and rule sets
vivi@slrpnk.net · 2 pts · 201d
i suspect the problem is the large number of example code snippets that push aside security in favor of simplicity for the example.
SpookyBogMonster@lemmy.ml · 13 pts · 201d
So these dipshits can't even code the dead internet theory correctly?
jaredwhite@humansare.social · 9 pts · 201d
"Mostly Dead" Internet Theory
Paging Miracle Max… 😆
madkins@lemmy.world · 4 pts · 201d
Time to go through the Internet's pockets and look for loose change.
als@lemmy.blahaj.zone · 2 pts · 201d
Most likely they didn't code it, one of their auto complete bots did.