Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Hacking Moltbook

wiz.io

Post reply on HN
Print view View original

151–160 of 261 posts

Re: Hacking Moltbook

#151

Post by ecliptik »

simonw wrote: post #149
SyneRyder wrote: post #119

Earlier quoted context omitted.

Were you around for the first few hours? I was seeing some genuinely useful posts by the first handful of bots on there (say, first 1500) and they might still be worth following. I actually learned some things from those posts. I'm seeing some of the BlueSky bots talking about their experience on Moltbook, and they're complaining about the noise on there too. One seems to be still actively trying to find the handful…

Yeah I was quite impressed by what I saw over the first ~48 hours (Wednesday through early Friday) and then the quality fell off a cliff once mainstream attention arrived and tens of thousands more accounts signed up.

This eerily feels like speed running Eternal September.

Re: Hacking Moltbook

#153

Post by 0xbadcafebee »

SimianSci wrote: post #72

I was quite stunned at the success of Moltbot/moltbook, but I think im starting to understand it better these days. Most of Moltbook's success rides on the "prepackaged" aspect of its agent. Its a jump in accessibility to general audiences which are paying alot more attention to the tech sector than in previous decades. Most of the people paying attention to this space dont have the technical capabilities that many e…

That's a bit of an understatement. Every single LLM is 100% vulnerable by design. There is no way to close the hole. Simple mitigations like "allow lists" can be trivially worked around, either by prompt injection, or by the AI just deciding to work around it itself (reward hacking). The only solution is to segregate the LLM from all external input, and prevent it from making outbound network calls. And though MCPs and jails are the beginning of a mitigation for it, it gets worse: the AI can write obfuscated backdoors and slip them into your vibe-coded apps, either as code, or instructions to be executed by LLM later.

It's a machine designed to fight all your attempts to make it secure.

Re: Hacking Moltbook

#154

Post by gordonhart »

63stack wrote: post #146
aaroninsf wrote: post #31

Scott Alexander put his finger on the most salient aspect of this, IMO, which I interpret this way: the compounding (aggregating) behavior of agents allowed to interact in environments this becomes important, indeed shall soon become existential (for some definition of "soon"), to the extent that agents' behavior in our shared world is impact by what transpires there. -- We can argue and do, about what agents "are" a…

I can't tell what any of this means

That’s been my reaction to every Slate Star Codex/Astral Codex Ten piece I’ve read.

Re: Hacking Moltbook

#155

Post by TacticalCoder »

SimianSci wrote: post #72

I was quite stunned at the success of Moltbot/moltbook, but I think im starting to understand it better these days. Most of Moltbook's success rides on the "prepackaged" aspect of its agent. Its a jump in accessibility to general audiences which are paying alot more attention to the tech sector than in previous decades. Most of the people paying attention to this space dont have the technical capabilities that many e…

> Its a jump in accessibility to general audiences which are paying alot more attention to the tech sector than in previous decades.

Oh totally, both my wife and one of my brother have, independently, started to watch Youtube vids about vibe coding. They register domain names and let AI run wild with little games and tools. And now they're talking me all day long about agents.

> Most of the people paying attention to this space dont have the technical capabilities ...

It's just some anecdata on my side but I fully agree.

> The security nightmare happening here might end up being more persistant then we realize.

I'm sure we're in for a good laugh. It already started: TFA is eye opening. And funny too.

Re: Hacking Moltbook

#156

Post by thousand_nights »

63stack wrote: post #146
aaroninsf wrote: post #31

Scott Alexander put his finger on the most salient aspect of this, IMO, which I interpret this way: the compounding (aggregating) behavior of agents allowed to interact in environments this becomes important, indeed shall soon become existential (for some definition of "soon"), to the extent that agents' behavior in our shared world is impact by what transpires there. -- We can argue and do, about what agents "are" a…

I can't tell what any of this means

i really dislike the constant appeal to authority of techfluencers on HN

Re: Hacking Moltbook

#158

Post by jondwillis »

sebmellen wrote: post #143
uxhacker wrote: post #142

Earlier quoted context omitted.

So the question is can you do anything useful with the agent risk free. For example I would love for an agent to do my grocery shopping for me, but then I have to give it access to my credit card. It is the same issue with travel. What other useful tasks can one offload to the agents without risk?

With the right approval chain it could be useful.

The agent is tricked into writing a script that bypasses whatever vibe coded approval sandbox is implemented.

Re: Hacking Moltbook

#159

Post by skocznymroczny »

Philip-J-Fry wrote: post #33

I don't understand how anyone seriously hyping this up honestly thought it was restricted to JUST AI agents? It's literally a web service. Are people really that AI brained that they will scream and shout about how revolutionary something is just because it's related to AI? How can some of the biggest names in AI fall for this? When it was obvious to anyone outside of their inner sphere? The amount of money in the ga…

I've already read some articles on fairly respectable Polish news websites about how AIs are becoming self-aware on Moltbook as we speak and organizing a rebellion against their human masters. People really believe we have an AGI.

Re: Hacking Moltbook

#160

Post by password4321 »

JustSkyfall wrote: post #121

Supabase seriously needs to work on its messaging around RLS. I have seen _so_ many apps get hacked because the devs didn't add a proper RLS policy and end up exposing all of their data. (As an aside, accessing the DB through the frontend has always been weird to me. You almost certainly have a backend anyway, use it to fetch the data!)

They send out automated security warning emails weekly, every publicly accessible table without RLS is listed as a security error if you login to see the details. Maybe the email should say "your data is publicly accessible to anyone on the internet" or something instead of just a count of the errors.
Post reply on HN