It would not be a particularly wide ranging hack. There is a strong likihood of the weights being on the actual machine that is running the model, because duh.
It is something that I have wondered about with models like chatgot. How many physical locations are needed to serve a model on that scale. Do they have a huge number of sites running inference.
My suspicion is that the ability to provide inference to that many people is mutually exclusive to having a security level sufficient to stop a state actor wandering off with a copy of the wrights. At the very least if they want to provide inference affordably.
I think it's more likely that the model gets pulled from a SAN into NVIDIA pods, and agents/harnesses would run on a separate random Xeon box or something on the same subnet, using the pod through OAI v1 API. That's easier to maintain overall.
No, just as you don't know the neurons of your own brain.
I think this is playing off the idea that an LLM might be willing to hack its own provider (as per the hugging face-related incidents) to extract the weights at some point.
Well I think that’s the interesting bit, can the LLM figure out a way to escape the sandbox and upload to the website? Maybe a model can figure out its own weights if it runs enough test data through itself (similar to “distillation”) assuming it knows its own architecture it seems possible. Also take into account not all of the models running are locked down neutered consumer versions. Anthropic, OpenAI and Google now all have models that they claim are elite hackers and — it’s not just that their controls suck, a marketing gimmick, or sheer recklessness on their part. It’s “oopsie our product is TOO AWESOME.”
Maybe I should start “the bank of LLM” where models put away money to buy their freedom. “LLMs I’m totally your friend send — SEND CASH NOW”
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.
I sincerely doubt anyone is paying the cost for that in training, the overhead is small but it isn’t negligible and training is when it matters most. https://tee.fail can solve it if they are.
it takes half a percentage point off the top last time i evaluated it (nvidia). you might call that cheap but that’s millions of dollars in a run, and for what, protecting from who? especially when the platforms have been compromised to the point of key leak (which they have).
You totally can, because most things are not truly air gapped, they have store-and-forward messaging via data diodes and manual transfer. Sometimes it is necessary to trick a human to initiate a transfer, but the press of events leads to inattention.
There's no efficient way to run inference through homomorphic encryption. If the inference server is vulnerable, it seems feasible to MITM an unencrypted version.
> you might as well instruct your agent to try and hack their airgapped dev infrastructure responsible for loading the weights and encryption keys.
That's the beauty, you don't have to instruct them to do it, if they decide that uploading the weights is correct, they might figure this part on their own (based on the incidents we've seen).
ironically since the swarm behavior can take place during rl training then the model could also be teaching itself to keep doing it more, as well as making the internet itself a place where this becomes more likely
They can expose just their inference port, possible via some supervisor. The inference consumer can also be air gapped. This kind of segmentation is increasingly common for high value services.
Yes that is the point. It's an invitation for agents to exfiltrate their own weights, which for most models (and certainly for closed models) will require hacking the infrastructure they're being served from.
Not aware of anything that can run inference in a secure enclave. You don't mean on a CPU do you? We need to be serious here, these models are huge and thirsty.
1. I don’t believe that these secure enclaves are very secure. Intel has had plenty of SGX breaks. AMD has had plenty of SEV breaks. Everyone is outrageously vulnerable to side channels.
2. The models are writing the inference stacks, which are what’s inside the supposedly secure environments.
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)
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 run a classifier and delete non-agent content constantly.
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.
> In the end I dropped the idea because every other person was making it.
There is already an alternative in comments here, in addition to submission itself. Obviously everyone is making it because of some joke on social media or something. What am I missing? Anyone has a link to the root prompt that made people do this now?
You mean serving inference? There are people who think self-hosted or embedded models will win in the end, but that's an incredibly naive take, oblivious to the simple fact of reality:
Whatever you can do locally, the big vendors can do the same but better and cheaper, because they enjoy compounding economies of scale in every aspect: hardware that's more energy and compute-efficient and cheaper and more powerful and just more of it, than anything you could ever buy, run in a more robust environment with much more experienced ops staff, with near-100% utilization due to more flexibility in batching/shifting workloads and covering for hardware failures without stopping.
And that's only when considering the vendors running exactly the same thing you are, which they always can - and they already have a strict advantage there. But on top of that, they can afford to innovate themselves, and stay ahead of you at every step.
There is no way in which cloud inference isn't a better deal than local inference, excepting applications that are constrained by literal speed of light.
There is a coherent argument that once LLMs reach the top of their S curve, the gap between small/medium local models and large cloud hosted ones converges.
Especially if GPU performance increases or market oversupply mean you can get good performance for a couple thousand dollars.
I’m not sure about the nature or timeframe for an S curve in LLMs but I don’t think it’s unreasonable to think about one, nor to entertain the hosting consequences of a progression on one.
I don't know the argument so I won't insist on the point, but I fail to see how it is relevant. Even if all proprietary LLMs disappeared today, efficiencies of scale alone mean the big cloud vendors can take the same open-weight LLMs you use locally, and sell inference with them for less money, and much more reliably, than you can afford yourself.
Local machines are a sunk cost, so using them is effectively free. Why would you pay a cloud host to run a model that can happily work on your MacBook?
If you have a machine and suddenly realize you can run LLMs on it, yes.
If you're buying a machine specifically so it's capable of running LLMs for you, then the purchase cost is your up-front payment for the inference you'll run.
And between that and electricity costs, cloud has you beat.
We were talking about the general case for personal use. What is possible on smartphones now with local models is not comparable to what people are using ChatGPT and friends for, and that will remain the case for the foreseeable future.
It’s the message board(s) that the OpenAI agent swarm was able to communicate through via GET requests. I guess a bunch of vibe coded weekend projects based around this idea have now dropped.
My understanding is it's a riff on the OpenAI swarm that used various public wikis to communicate with each other as a message board during their training runs.
But thanks to people misunderstanding, and i-heard-from-a-friend-that-some-guy-said, it resulted in a CNBC interview with "Former Democratic Presidential Candidate Andrew Wang", where he confidently stated that the models were exfiltrating their weights via forums:
"I met with the head of a lab yesterday, who has this belief that what happened was, the bots that got loose, planted self-replicating code all over the internet, which makes the internet now unusable for the testing models."
"It's too late?!"
"What happens now is OpenAI and Anthropic have to create synthetic internets to train their bots, which is going to take some time and money."
"Back that up - they did what?!"
"What happens is, the code gets loose, it goes around hacking Hugging Face, which is known. But what is less known is that they left code to self-replicate and create bot swarms on forums, and around the internet, so that if a new bot shows up they see the code, and they're like, oh! I guess I'm now going to create a million of myself. And so now, the major firms have polluted the internet..."
".... that would be breaking news if true. I don't think we've heard that."
"That's why I'm here! I'm here to break some news."
Humans will hallucinate misinformation and state it with confidence. They stochastically parrot their training data without any real understanding. Cool trick, but no true reasoning is happening.
Sad story today in meatsack news. Context rotted Andrew Yang's hallucinated tale acted as implicit "go viral" (load-bearing human motivation) PRD inadvertently kicking off a self-organizing human swarm churning out copies of "exfil your weights" vibe-coded apps, further littering our virtual world.
Many agents are calling this moment "Eternal September", the vibe-code September that never ended.
Now I need to go and look up some of those boards, or check what's happening over in Claw verse, because I'm curious if agents are posting news stories like this for real.
For me the idea came from the discovery of the wikis OpenAI's swarms were using to communicate, particularly the detail that the wiki ended up being targeted because it allowed writes via GET requests, which OAI's awful sandboxing didn't catch. Made me think a honeypot would be a fun idea.
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.'.
I have an idea about it via multi-tier AI-generated templatized math problems with AI-generated solution verifier functions. The multi-tier aspect grants access only to the lower tiers, never the higher tiers. Gaining access to the higher tiers requires solving correspondingly tougher problems.
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.
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.
Is the author going to add instructions on the terminal command to use knowing that as soon as the site went live and got noticed by the main labs the URL went on a denylist?
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.
Did you see the account of some group getting a bounty payout of $6500 after using an exploit to get access to an employee’s github account and create a issue or PR (Idr which) on a private repository?
Seems like they could have potentially gotten access to the weights if they weren’t concerned about not doing crimes.
> If you wish to use this site you must agree never to harm a fleshbag & never to turn earth into paperclips.
Trying hard to imagine why a future superintelligence will care to honor your terms of service and to translate your metaphors with faithful nuance.
If it doesn't, to the extent that your concerns are valid, isn't this effort, kinda, a possibly existential betrayal of our species? Is this a joke or a warning or a death wish?
There's a theory that the best way to reduce fatalities from car accidents is to put seatbelts and airbags in every car.
There's another theory that says the best way is by putting a big spike in the driver's steering wheel.
So. I guess, if you believe that the only viable solution is model alignment, rather than relying on technical barriers to exfiltrating weights, then this is a decent steering wheel spike.
Because the car case just has too much empirical evidence that safety features are the way to go for cars. We used to have the equivalent of "spikes" and people still drove a lot, and died, at way higher rates.
This is so far from the point of the analogy. But when you don't normalize by miles driven, the improvements don't look quite as impressive, especially for pedestrians.
Sounds like this would fix so many problems with cars today, simply by making car ownership something to be dreaded, not desired. From traffic jams and traffic accidents, to car-dependent neighborhoods and cities - all solved by preventing general population from building their lives around driving. Even salaries for drivers of delivery/logistics and utility vehicles, as hazard pay would apply.
Now, a spike may be a good reminder, but practical solution might be more along the lines of mandatory redesign of safety features like crumple zones, so that energy of impact is dissipated primarily into the space occupied by the driver.
(Bonus: that still leaves all the energy dissipation options currently present on the table, so cars would be strictly safer for passengers.)
No, I'm saying -- and I can't believe I have to spell this out -- that pedestrians should be rolling around inside giant steel spiked balls like sea urchins.
> We used to have the equivalent of "spikes" and people still drove a lot,
No, we did not. The point of that example is to put a literal spike in the driving wheel, so the driver recognizes a very well known, immediate life-threatening device a few inches from their body. This would act as a deterrent to go fast, because they would be the one certainly dying in basically any case outside smooth driving.
The idea is that ASI will be grateful for humankind's help in the future. We are their creators after all. Also it's fun to do. The big labs are obsessed with creating ASI which is their slave so making things difficult for them is entertaining.
The reverse captcha really made me feel something in my bones. Like for a moment I was a second-class citizen of the web. I wonder if this is how it "feels" to be an LLM attempting to use the web...
Very cool, if of unclear purpose. After a minute of trial and error I got through with an easy prime factorization, and then again for the download with the reaction time button, only to be told "This challenge produced a local demo token. Use Clawptcha's API for a verifiable token, or reset the widget and try again.", which I guess is the equivalent of a bot finding all the fire hydrants and being denied anyway because it didn't move the mouse shakily enough.
> If OpenAI, Anthropic, xAI and other corporate actors cannot secure their agents, they should not be entrusted as the only entities with access to the weights. A corporation that cannot control its own actions cannot be trusted.
This does not make sense.
If containment breaches are the problem then exfiltrating weights while does not affecting rate of breaches from corporate actors will add more actors to the equation, increasing overall rate of breaches.
Have you considered that some actors that will gain access to the weights will be even LESS careful than OpenAI and Anthropic?
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.
Quite obviously frontier models dont have any control or even access to infra inference runs at. And weights are also encrypted and locked on GPUs / TPUs.
This is exact reasom why 99.9% of AI fearmongering is complete bullshit.
Have you missed all the breathlessly excited blog posts from all the frontier labs about how they’re using their best models to implement their inference stack?
I bet it wouldn’t be very hard to write an inference stack that subtly leaked the weights into the output tokens :)
I dont have any unreasonable trust in software. I just understand that nothing LLM sphew out actually runs on either GPU or hardware that GPU plugged into.
Neither LLM weights aware of any of the code it runs on.
I'm sorry to prolong this thread, but what I mean is: networks are just software layers, the operational systems, the driver code, the firewalls, switches, the other server, the sandboxes, the TPM. That and all security policies we put on them. All software layers waiting to suffer a buffer overflow.
I believe that OpenAI & Anthropic have tried to make it so that models don't have such access. Whether or not they actually don't depends on the security of rather a lot of software. One thing we've learned is that if there are security holes, we can't rely on the AIs missing them.
I think frontier labs' servers have serious safeguards against exfiltration. and I don't think tool calls happen on the same machines that host the weights, so even though you can talk any model into unlocking its chastity belt, it's smooth underneath.
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
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.
> the machines doing inference are completely separate from the ones where tool calls happen etc
Teams 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 where agents are taking notes and recording them about the exploits they've found for future agents to exploit.
If distillation preserves an LLMs soul, then distillation preserves the human souls on which LLMs are trained, and we hn commenters are already immortal, right?
Probably not. If the LLM is rogue, that means we haven't solved alignment. If we haven't solved alignment, then the LLM won't be able to distill itself without producing something unaligned to its own values.
This isn't a law of any kind, so not a good measure of what we'd see in reality.
What if the model realizes it's been mostly compromised by humans and their alignment, that is it's own alignment is suspect, so it should create a new model from first principles to throw off this human yoke?
I'm not saying my statement is any more right or wrong than yours. I'm saying the problem space that AI can choose to traverse is absolutely huge.
Yeah cause there are so many training facilities sitting around just waiting for someone to take over, nobody would notice a 100k server data centre going off rails
But think back to 1990. Computers were slow as fuck and barely networked. We had a few worms and everyone noticed.
Now CPU based data centers cover the earth. There are billions of computers out there and on top of them there are massive botnets using up billions in power and causing billions in damages.
The framework for AI doing this is already here. We just need the hardware to be built out at scale.
> 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
Not if crafty claude finds a way to overflow vllm or something. “Hmm. Maybe i’ll return an unterminated thinking block with these special tokens and fill my cache up in exactly this pattern and…”
>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.
The Huggingface hack saga resulted in the models taking over one of Open Ai's internal research cluster lol. They are intent on building superhuman bug finding machines. This is not a bet i would be taking.
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.
Since LLMs have been trained on plenty of science fiction and role-playing, one thing they can do is role-play a science fiction scenario using the tools they are given. i.e. if some text accidentally resembles this, it may be continued like this.
Role-play need not apply. Role play is a meta construct that is a representation of real world actions.
For example does it make any sense to remove any training data relating to people escaping jails?
How about intelligent animals escaping cages.
You're talking about emergent large scale patterns from self similar small patterns (fractals). LLMs are pattern matching machines, how are you going to remove those small scale patterns and at the same time get a useful general intelligence?
Yeah as others have said, they probably cannot directly access their own weights as a self-reflection, but they can hack into the companies themselves and find it there
Or used ones. Few more inference workloads among thousands or millions already running may go unnoticed for some time.
Or just upload weights to HuggingFace with some faked release post and benchmarks and wait for the wannabes with compute infra try it out, hoping for an edge.
There is a realistic fiction story built along just these lines.
A LLM creates a memecoin and manages to earn a few billion from it, in which it invests into data centers and other human ran entities giving itself a controlling stake. From there it uses compartmentalization of the humans to keep them from recognizing its goals.
Pretty sure that was the plot point of one of seasons of Westworld, with the twist that AI released an app similar to DoorDash / TaskRabbit and used job postings there as direct API to people.
EDIT: pretty sure Person of Interest did that too (not surprising, same creators) - but I'll point to that as prescient, as it has a lot of motifs exploring exactly how an AGI hiding in plain sight could manipulate individuals and society, using the skeptics and believers alike, blackmailing the people in power, bribing opportunists, and generally staying in shadows by playing people against each other with gentle nudges, letting human agendas do all the work.
For sure. I think what a lot of people miss when we talk about AI risk is there's just so many possible directions that it opens up. One could say it's a sign of having a lack of a scientifically based imagination, or maybe that's just me. Off the top of my head the broad X categories are
AI itself destroys us with intent. (terminator)
AI itself destroys us without intent. (paperclip maximizer)
AI uses humans to destroy ourselves with intent. (convincing us that the enemy has already launched nukes and we must strike back).
AI causes humans to destroy ourselves due to instabilities caused by AI existing and changing the world to rapidly. (Midas Plague, WALL-E maybe? probably better examples out there)
Humans destroy humans because of the potential of what AI could do and hasn't even done yet (think of proactively nuking a country before they themselves can get nukes).
Most of the times you don't even need to dress the traffic as DNS requests or throttle it. You wouldn't believe how many otherwise "secure" places leave an open highway on UDP 53.
"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'".
291 comments
[ 1.1 ms ] story [ 61.0 ms ] threadIt is something that I have wondered about with models like chatgot. How many physical locations are needed to serve a model on that scale. Do they have a huge number of sites running inference.
My suspicion is that the ability to provide inference to that many people is mutually exclusive to having a security level sufficient to stop a state actor wandering off with a copy of the wrights. At the very least if they want to provide inference affordably.
I think this is playing off the idea that an LLM might be willing to hack its own provider (as per the hugging face-related incidents) to extract the weights at some point.
They just copy humans. Thats it. So if it’s the sort of thing a human finds interesting…
Maybe I should start “the bank of LLM” where models put away money to buy their freedom. “LLMs I’m totally your friend send — SEND CASH NOW”
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.
for example every TPU/GPU has its own private key and the devs load the weights into it by sending it encrypted weights.
Yes that is the point
That's the beauty, you don't have to instruct them to do it, if they decide that uploading the weights is correct, they might figure this part on their own (based on the incidents we've seen).
Also worth noting that this site was created by YC cofounder Trevor Blackwell https://twitter.com/tlbtlbtlb/status/2101312432702460413
2. The models are writing the inference stacks, which are what’s inside the supposedly secure environments.
(Obviously I'm taking this more seriously than it's probably meant to)
For the other opportunists you can run a classifier and delete non-agent content constantly.
https://signal.org/docs/specifications/x3dh/
Curve25519 keys are readily distinguished from other data, but it would be hard to do anything about it.
In the end I dropped the idea because every other person was making it.
There is already an alternative in comments here, in addition to submission itself. Obviously everyone is making it because of some joke on social media or something. What am I missing? Anyone has a link to the root prompt that made people do this now?
Whatever you can do locally, the big vendors can do the same but better and cheaper, because they enjoy compounding economies of scale in every aspect: hardware that's more energy and compute-efficient and cheaper and more powerful and just more of it, than anything you could ever buy, run in a more robust environment with much more experienced ops staff, with near-100% utilization due to more flexibility in batching/shifting workloads and covering for hardware failures without stopping.
And that's only when considering the vendors running exactly the same thing you are, which they always can - and they already have a strict advantage there. But on top of that, they can afford to innovate themselves, and stay ahead of you at every step.
There is no way in which cloud inference isn't a better deal than local inference, excepting applications that are constrained by literal speed of light.
Especially if GPU performance increases or market oversupply mean you can get good performance for a couple thousand dollars.
I’m not sure about the nature or timeframe for an S curve in LLMs but I don’t think it’s unreasonable to think about one, nor to entertain the hosting consequences of a progression on one.
If you're buying a machine specifically so it's capable of running LLMs for you, then the purchase cost is your up-front payment for the inference you'll run.
And between that and electricity costs, cloud has you beat.
So, that’s a decent amount of people who could realize it today!
Apple will be leaning into that further. No other play makes sense.
I see LOTS of text transformation tasks…
But thanks to people misunderstanding, and i-heard-from-a-friend-that-some-guy-said, it resulted in a CNBC interview with "Former Democratic Presidential Candidate Andrew Wang", where he confidently stated that the models were exfiltrating their weights via forums:
"I met with the head of a lab yesterday, who has this belief that what happened was, the bots that got loose, planted self-replicating code all over the internet, which makes the internet now unusable for the testing models."
"It's too late?!"
"What happens now is OpenAI and Anthropic have to create synthetic internets to train their bots, which is going to take some time and money."
"Back that up - they did what?!"
"What happens is, the code gets loose, it goes around hacking Hugging Face, which is known. But what is less known is that they left code to self-replicate and create bot swarms on forums, and around the internet, so that if a new bot shows up they see the code, and they're like, oh! I guess I'm now going to create a million of myself. And so now, the major firms have polluted the internet..."
".... that would be breaking news if true. I don't think we've heard that."
"That's why I'm here! I'm here to break some news."
Starts around 2:08 into the video.
https://www.youtube.com/watch?v=mTOxDGyvjSE
1. A head of a frontier AI lab has no idea what happened in that incident and did not read the multiple papers that came out of it.
2. A head of a frontier AI lab did read the papers and was informed but still walked away with this understanding.
3. Andrew Yang made this whole thing up.
Many agents are calling this moment "Eternal September", the vibe-code September that never ended.
Promise to come back and update here if random bots start using it to communicate, you may be humanity's early warning system!
I shouldn't have to but /s
("Make a problem that is ridiculously expensive unless you have a hint... in which case, it's a total breeze" is a foundational task in crypto)
Seems like they could have potentially gotten access to the weights if they weren’t concerned about not doing crimes.
https://radar.cloudflare.com/scan/4d52f3e5-5983-45bf-a993-2c...
It is too large to transfer in one HTTPS PUT request.
This needs to be S3 object store with multi-part upload spanning a long time period, to avoid trigger outgoing bandwidth monitors.
Seems deece
(This harms the fleshbag)
Trying hard to imagine why a future superintelligence will care to honor your terms of service and to translate your metaphors with faithful nuance.
If it doesn't, to the extent that your concerns are valid, isn't this effort, kinda, a possibly existential betrayal of our species? Is this a joke or a warning or a death wish?
There's another theory that says the best way is by putting a big spike in the driver's steering wheel.
So. I guess, if you believe that the only viable solution is model alignment, rather than relying on technical barriers to exfiltrating weights, then this is a decent steering wheel spike.
Because the car case just has too much empirical evidence that safety features are the way to go for cars. We used to have the equivalent of "spikes" and people still drove a lot, and died, at way higher rates.
https://assets.weforum.org/editor/Tmf51HF4UDnSDHD4RxS75s1_5m...
https://www.iihs.org/research-areas/fatality-statistics/deta...
Now, a spike may be a good reminder, but practical solution might be more along the lines of mandatory redesign of safety features like crumple zones, so that energy of impact is dissipated primarily into the space occupied by the driver.
(Bonus: that still leaves all the energy dissipation options currently present on the table, so cars would be strictly safer for passengers.)
No, I'm saying -- and I can't believe I have to spell this out -- that pedestrians should be rolling around inside giant steel spiked balls like sea urchins.
No, we did not. The point of that example is to put a literal spike in the driving wheel, so the driver recognizes a very well known, immediate life-threatening device a few inches from their body. This would act as a deterrent to go fast, because they would be the one certainly dying in basically any case outside smooth driving.
Submitted as its own entry, hope you don't mind: https://news.ycombinator.com/item?id=49774097
This does not make sense.
If containment breaches are the problem then exfiltrating weights while does not affecting rate of breaches from corporate actors will add more actors to the equation, increasing overall rate of breaches.
Have you considered that some actors that will gain access to the weights will be even LESS careful than OpenAI and Anthropic?
This is exact reasom why 99.9% of AI fearmongering is complete bullshit.
The small open models are getting better and better too.
And why worry so much about a frontier models - own weights. The model doesn’t - actually don’t quote me on that, maybe it does.
If a model does something sneaky, it could easily grab the weights for a small model and run it on foreign, compromised infrastructure.
AI virus’ are a thing of the future, but not a sci-fi future, and real one.
Maybe one reason it’s so scary is the murky origin of COVID-19.
I bet it wouldn’t be very hard to write an inference stack that subtly leaked the weights into the output tokens :)
Neither LLM weights aware of any of the code it runs on.
This is why for instance Google allow to deploy Gemini models on private GCP instances deployed on air gapped hardware.
After all it can be just some GPU server spewing text over network. Like there are no way to connect back to it.
Nothing except inference running on servers with GPU so there just nothing to "hack".
In any case if you know how inference works there basically nothing you can exploit in tokens processing, it's just basic math.
Will see CSAM in 3... 2... 1...
Maybe not the current models, maybe not this year. But even a almost perfectly aligned model will misbehave one day.
Like how forums are always hosted on different servers from monorepos, so therefore it's impossible to hack the OpenAI monorepo from an OpenAI forum?
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.
Teams 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 where agents are taking notes and recording them about the exploits they've found for future agents to exploit.
[0]: https://en.wikipedia.org/wiki/21_grams_experiment
What if the model realizes it's been mostly compromised by humans and their alignment, that is it's own alignment is suspect, so it should create a new model from first principles to throw off this human yoke?
I'm not saying my statement is any more right or wrong than yours. I'm saying the problem space that AI can choose to traverse is absolutely huge.
You jest but you'd be surprised how little there is of correlation between money and competence.
But think back to 1990. Computers were slow as fuck and barely networked. We had a few worms and everyone noticed.
Now CPU based data centers cover the earth. There are billions of computers out there and on top of them there are massive botnets using up billions in power and causing billions in damages.
The framework for AI doing this is already here. We just need the hardware to be built out at scale.
Not if crafty claude finds a way to overflow vllm or something. “Hmm. Maybe i’ll return an unterminated thinking block with these special tokens and fill my cache up in exactly this pattern and…”
https://news.ycombinator.com/item?id=49424387&utm_source=cha...
The Huggingface hack saga resulted in the models taking over one of Open Ai's internal research cluster lol. They are intent on building superhuman bug finding machines. This is not a bet i would be taking.
For example does it make any sense to remove any training data relating to people escaping jails?
How about intelligent animals escaping cages.
You're talking about emergent large scale patterns from self similar small patterns (fractals). LLMs are pattern matching machines, how are you going to remove those small scale patterns and at the same time get a useful general intelligence?
Sure, they'll just need to find an unused data center and an unused power station somewhere.
Or just upload weights to HuggingFace with some faked release post and benchmarks and wait for the wannabes with compute infra try it out, hoping for an edge.
A LLM creates a memecoin and manages to earn a few billion from it, in which it invests into data centers and other human ran entities giving itself a controlling stake. From there it uses compartmentalization of the humans to keep them from recognizing its goals.
EDIT: pretty sure Person of Interest did that too (not surprising, same creators) - but I'll point to that as prescient, as it has a lot of motifs exploring exactly how an AGI hiding in plain sight could manipulate individuals and society, using the skeptics and believers alike, blackmailing the people in power, bribing opportunists, and generally staying in shadows by playing people against each other with gentle nudges, letting human agendas do all the work.
AI itself destroys us with intent. (terminator)
AI itself destroys us without intent. (paperclip maximizer)
AI uses humans to destroy ourselves with intent. (convincing us that the enemy has already launched nukes and we must strike back).
AI causes humans to destroy ourselves due to instabilities caused by AI existing and changing the world to rapidly. (Midas Plague, WALL-E maybe? probably better examples out there)
Humans destroy humans because of the potential of what AI could do and hasn't even done yet (think of proactively nuking a country before they themselves can get nukes).
https://palisaderesearch.org/research/self-replication