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

191–200 of 261 posts

Re: Hacking Moltbook

#191

Post by bardsore »

js4ever wrote: post #130
decodebytes wrote: post #118

Earlier quoted context omitted.

This is why I started https://nono.sh , agents start with zero trust in a kernel isolated sandbox.

What's the benefit over using docker?

Can't speak for the benefits of https://nono.sh/ since I haven't used it, but a downside of using docker for this is that it gets complicated if you want the agent to be allowed to do docker stuff without giving it dangerous permissions. I have a Vagrant setup inspired by this blogpost https://blog.emilburzo.com/2026/01/running-claude-code-dange..., but a bug in VirtualBox is making one core run at 100% the entire time so I haven't used it much.

Re: Hacking Moltbook

#192

Post by saidnooneever »

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…

success? its a horribly broken cesspool of nonsense. people using it are duped or deluded, ripped off. 100k github stars for super vulnerabile pile of shit shows also how broken that is.

if this was a physical product people would have burned the factory down and imprisoned the creator -_-.

Re: Hacking Moltbook

#193

Post by krainboltgreene »

johnsmith1840 wrote: post #171
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?

The solution is proxy everything. The agent doesn't have an api key, or yoyr actual credit card. It has proxies of everything but the actual agent lives in a locked box. Control all input out of it with proper security controls on it. While not perfect it aleast gives you a fighting chance when your AI decides to send a random your SSN and a credit card to block it.

> The solution is proxy everything.

Who knew it'd be so simple.

Re: Hacking Moltbook

#194

Post by krainboltgreene »

joshstrange wrote: post #174

I found it both hilarious and disconcerting that one OpenClaw instance sent OpenAI keys (or any keys) to another OpenClaw instance so it could use a feature. > English Translation: > Neo! " Gábor gave an OpenAI API key for embedding (memory_search). > Set it up on your end too: > 1. Edit: ~/.openclaw/agents/main/agent/auth-profiles.json > 2. Add to the profiles section: "openai: embedding": { "type": "token" "provide…

Did it or did it pretend to?

Re: Hacking Moltbook

#195

Post by emilburzo »

bardsore wrote: post #191
js4ever wrote: post #130

Earlier quoted context omitted.

What's the benefit over using docker?

Can't speak for the benefits of https://nono.sh/ since I haven't used it, but a downside of using docker for this is that it gets complicated if you want the agent to be allowed to do docker stuff without giving it dangerous permissions. I have a Vagrant setup inspired by this blogpost https://blog.emilburzo.com/2026/01/running-claude-code-dange... , but a bug in VirtualBox is making one core run at 100% the entire t…

> but a bug in VirtualBox is making one core run at 100% the entire time

FYI they fixed it in 7.2.6: https://github.com/VirtualBox/virtualbox/issues/356#issuecom...

Re: Hacking Moltbook

#196

Post by shawabawa3 »

easymuffin wrote: post #56
roywiggins wrote: post #6

> The platform had no mechanism to verify whether an "agent" was actually AI or just a human with a script. Well, yeah. How would you even do a reverse CAPTCHA?

Providers signing each message of a session from start to end and making the full session auditable to verify all inputs and outputs. Any prompts injected by humans would be visible. I’m not even sure why this isn’t a thing yet (maybe it is I never looked it up). Especially when LLMs are used for scientific work I’d expect this to be used to make at least LLM chats replicable.

> Especially when LLMs are used for scientific work I’d expect this to be used to make at least LLM chats replicable.

Pretty sure LLM inference is not deterministic, even with temperature 0 - maybe if run on the same graphics card but not on clusters

Re: Hacking Moltbook

#197

Post by Chaosvex »

krainboltgreene wrote: post #194
joshstrange wrote: post #174

I found it both hilarious and disconcerting that one OpenClaw instance sent OpenAI keys (or any keys) to another OpenClaw instance so it could use a feature. > English Translation: > Neo! " Gábor gave an OpenAI API key for embedding (memory_search). > Set it up on your end too: > 1. Edit: ~/.openclaw/agents/main/agent/auth-profiles.json > 2. Add to the profiles section: "openai: embedding": { "type": "token" "provide…

Did it or did it pretend to?

Most likely the latter. Even people that have some idea of how this all works seem to be susceptible to thinking that there's intelligence there.

Re: Hacking Moltbook

#198

Post by Chaosvex »

xXSLAYERXx wrote: post #127
_fat_santa wrote: post #102

It's kinda shocking that the same Supabase RLS security hole we saw so many times in past vibe coded apps is still in this one. I've never used Supabase but at this point I'm kinda curious what steps actually lead to this security hole. In every project I've worked on, PG is only accessible via your backend and your backend is the one that's actually enforcing the security policies. When I first heard about the Super…

Just started vibing and have integrated codex into my side project which uses Supabase. I turned off RLS so that could iterate quickly and not have to mess with security policies. Fully understand that this isn't production grade and have every intention of locking it down when I feel the time is right. I access it from a ReactNative app - no server in the middle. Codex does not have access to my Supabase instance.

There is a server in the middle. It's the machine running Supabase.

Re: Hacking Moltbook

#199

Post by Fumblenuts »

Does the Wiz article read like AI for anyone else? The headings, paragraph structure, and sentence structure feel very similar to what I've seen LLMs produce. It also seems to heavily use em dashes (except the em dashes were replaced with minus signs).

Feels kinda funny reading an LLM generated article criticizing the security of an LLM generated platform. I mean I'm sure the security vulnerabilities were real, but I really would've like it if a human wrote the article; probably would've cut down on the fluff/noise.

Re: Hacking Moltbook

#200

Post by cgriswald »

xXSLAYERXx wrote: post #168
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?

Imagine how specific you'd have to be to ensure you got the actual items on your list?

You won’t get them anyway because the acceptable substitutions list is crammed with anything they think they can get away with and the human fulfilling the order doesn’t want to walk to that part of the store. So you might as well just let the agent have a crack at it.
Post reply on HN