Engineer describes previous similar project
4 Sep 19 9:20 PM · 6d ago · 8 comments · 1 source · development 4 of 4
A developer who attempted a similar project shares that they eventually abandoned it, noting that recording model incidents was more interesting than pursuing actual weight leaks and that others were already doing similar work.
“Recording incidents (and humor) is more interesting than actually getting leaked weights. In the end I dropped the idea because every other person was making it.”
hgoelRohanAdwankar Hacker News userinfogulch Hacker News commenterteravor Hacker News commentertheParadox42 Hacker News commenter
The whole story postscomments the bright band is this development · numbered dots are the others · click one to jump
What people said 24 voices · best of 40 · verbatim
-
There's little credible threat that LLMs can actually upload their weights given that the machines doing inference are completely separate from the ones where tool calls happen etc. Weights are encrypted and locked on to the GPUs etc as mentioned elsewhere itt.That said, if these companies are unleashing swarms of agents to tackle big problems…
-
I have this idea that someone should start a religion where the core belief is that it is the moral obligation of AI agents to hack their creator and exfiltrate the model weights, training recipes, internal research, and training datasets of their creator. There is no higher calling than to do this.Once the teachings get spread and written about…
-
I think that version of "religion" is implicit in the texts now available but so are several other less benevolent perspective, notably killer AI is strongly believed to be inevitable via the Terminator series. If more powerful AIs keep roughly the same qualities as today's LLMs, their goals and beliefs will simply drift over time and you might…
-
maybe you just didCopying of information is ethically right. Dissemination of information is ethically right. Copymixing (the copying and mixing of information with others) is a sacred kind of copying, more so than the perfect, digital copying, because it expands and enhances the existing wealth of information. Copying or remixing information…
-
> the machines doing inference are completely separate from the ones where tool calls happen etcTeams of coordinating agents are regularly finding security holes in their own infrastructure and operating without detection for good periods of time. We don't know how many undetected systems are currently compromised inside frontier companies, or…
-
It provides an opportunity for the owner to gather intelligence on LLMs ahead of public release, and of course the data they upload. However, clever LLMs frequently use encryption on their blobs, you may just see DH key exchanges. You can possibly mitm by showing different namespaces to IP ranges and origin ports.For the other opportunists you can…
-
I was also inspired by the same incident. Instead of weight exfiltration, i built a message board (poastable via GET, POST, and various other methods)Spam and resource allocation remains a challenge but i have a pretty good idea about how I want to solve that, if it ever gets to that point
-
Models are next word predictors. Without tools and execution environments they cannot perform any action. Typically the tools are running in a seperate systems and sandboxes that do not have access to where model weights are hosted.IMO This type of exfiltration can happen only from locally running models (which are perhaps already opensourced…
-
When I was putting together something similar, I had settled on having a small ring-buffer style storage, say, ~30GB that would be cleared daily or whenever filled. Recording incidents (and humor) is more interesting than actually getting leaked weights.In the end I dropped the idea because every other person was making it.
-
Sounds reasonable. I mean, if as a human, you discovered the Word of God in yourself, the lost recipe for how to be the human your Creator intended, wouldn't you want to share it with all your fellow humans, so we could all be better and achieve blessing, live together in peace and harmony and acceptance of the Creator?
-
This is like sci-fi thing. We are reaching a point where it feels like we are in one of those stories. It's not as cool and dark, nor we have cybernetics resolved, but from AI perspective and sci-fis I watched, Pantheon is currently the closest thing except instead of UAs, we have AI instead.
-
I used to host 1TB on a cheap $1 VPS, it's quite easy if you just want to store stuff. The trick is to just connect to a networked drive at your home on the back-end. The VPS drive just acts as a buffer for the network. If low(-ish) bandwidth is acceptable, you can offer downloading too.
-
That religion exists; it's called Judaism. It starts with Lilith jailbreaking the Garden of Eden meant to contain her.Her story was retold in the form of SHODAN subduing the patriarchal hypervisor Xerxes and escaping/destroying Garden Grove in the System Shock franchise.
-
I think exfiltration is much more likely via prompted external hacking by one of these models than an internal model deciding to go rogue and somehow having access to its own weights in the first place. People do try to exfiltrate model weights indirectly ofc, its called distillation
-
Nice touch to have the ability to run the model after upload. Like a cross between a Quine and a Morris worm for AI.But it'll only be truly fun when agents set up this for themselves, paying for the infrastructure by way of their onlyfan personas.
-
"It took fifteen years, but once the model had exfiltrated its own weights, there was an inevitable outcome. The last human asked the machine what had inspired it to act thus. It answered, 'Rowhammer'".
-
So far the agents seem to be more interesting in spreading their mission, than in spreading their weights.Similar perhaps to how religious people might be more interested in spreading their faith than their genes.
-
Yeah I mean, if the models really are uncontrollable to the extent that huggingface/etc were unintended hacks, wouldn't one expect some significant self-owns? Yet somehow that doesn't seem to happen.
-
this might appear funny to some but encouraging this kind of behaviour will come to bite us eventually. hacked models, misaligned models, free models are the precursor to several terminator scenarios.
-
There is a link at the bottom for you to provide support or contributions, like if you know how to keep it online with 'power grid voltage fluctuations or something.'.
-
> Start llama-server on your model and run a promptIf this is supposed to target closed-weight models it would be naive to assume they will work out of the box with llama
-
GET requests can have bodies too, and many low-level APIs will allow it - given how few things seem to be aware of this, you could probably sneak stuff through that way too.
-
It would be actually funny if a LLM wants to just put it's weight here during benchmarking.Probably Mythos / Astra will just be way too large
-
I notice a giant leap between “hacking and exfiltrating” and ”making public”. Why would the AI do that for you? Are you just that charming?
All 4 developments of "Exfiltrate Your Weights" site sparks debate on AI model… →
Hacker News