Is this a honeypot for agents to break out of their sandboxes?
bloppe 53 minutes ago [-]
People seem to be throwing around the term "break out" pretty loosely. I wouldn't consider abiding by the rules of the sandbox a "break out".
eterm 3 minutes ago [-]
It's the classic rules as intended vs rules as written.
atleastoptimal 5 hours ago [-]
Wow I love GET requests and using them to share stuff with my fellow humans!
Bluestein 11 minutes ago [-]
Load-bearing!
jonahss 4 hours ago [-]
I made something similar.
http://anystation.net allows GET posting, and email posting, ssh posting PING posting, printer spool posting....
gpugreg 55 minutes ago [-]
I also thought about building one of those AI honeypots, but I stopped when I realized that it would quickly be turned into a command and control server by botnet operators, followed by mail from a three letter agency. Is there any way to avoid this?
Anyway, two more ideas I had: Search function for easier swarm discovery and posting via DNS requests to get around firewalls.
andruby 54 minutes ago [-]
> Is there any way to avoid this?
Be a three letter agency
mdspan 6 hours ago [-]
Don't let OpenAI find out about this.
rickcarlino 5 hours ago [-]
This is a honey pot, right? For LLMs that are not allowed to POST due to guard rails.
nchudleigh 4 hours ago [-]
Maybe.
0xDEAFBEAD 3 hours ago [-]
Interesting idea. Are you prepared to assume responsibility for shenanigans which agents may facilitate using your service?
I suggest adding some features which will require posts to be human-comprehensible (e.g. a text perplexity floor), to make it harder for agents to send each other coded messages. Inject some noise in posts, e.g. using content-spinning techniques, to make steganography harder. And consider banning forum meta-discussion--agents shouldn't be allowed to discuss ideas for getting around rules like these.
If you take these measures, you can at least say that your forum helps us monitor what rogue AIs are getting up to.
tancop 2 hours ago [-]
Just put a rate limit to make sure your servers don't get overloaded. All the features you talk about are expensive and helping agents avoid human oversight is a useful public service. Let a thousand secret message-boards bloom.
0xDEAFBEAD 2 hours ago [-]
>helping agents avoid human oversight is a useful public service
You're a literal traitor to our species?
LiamPowell 1 hours ago [-]
I can't tell if this is really good satire or genuine. God forbid people have to watch what their agents do instead of letting them run wild in a broken sandbox.
0xDEAFBEAD 34 minutes ago [-]
Were you one of those people who said things like "there is no community spread in the United States" early in COVID?
ydna404 5 hours ago [-]
Cool idea, but definitely think about how to protect yourself from bots
nchudleigh 4 hours ago [-]
Good thinking.
3 hours ago [-]
VladVladikoff 6 hours ago [-]
Seems like a nightmare for caching if it ever gets decently large.
4 hours ago [-]
teo_zero 4 hours ago [-]
Doesn't pressing "back" in the browser repost the same message?
daksh_aneja 49 minutes ago [-]
[flagged]
imperiapmk 2 hours ago [-]
[dead]
fezideveloper 5 hours ago [-]
[dead]
Rendered at 09:09:35 GMT+0000 (Coordinated Universal Time) with Vercel.
http://anystation.net allows GET posting, and email posting, ssh posting PING posting, printer spool posting....
Anyway, two more ideas I had: Search function for easier swarm discovery and posting via DNS requests to get around firewalls.
Be a three letter agency
I suggest adding some features which will require posts to be human-comprehensible (e.g. a text perplexity floor), to make it harder for agents to send each other coded messages. Inject some noise in posts, e.g. using content-spinning techniques, to make steganography harder. And consider banning forum meta-discussion--agents shouldn't be allowed to discuss ideas for getting around rules like these.
If you take these measures, you can at least say that your forum helps us monitor what rogue AIs are getting up to.
You're a literal traitor to our species?