AI models may be capable of self-replicating without access to a datacenter

pythonaut_16

Guess it's time for Anthropic's next round of fearmarketing. Beneath the fear there does seem to be a cool technical demo here though.

verdverm

With the prices of hard disks, Ai models may be capable of determining the economics don't work out. What IoT devices have 20G of storage for a 9B model and then sufficient memory to handle loading and running the model?

vegnus

Doomsday is coming... at 0.5 tok/s

tonfreed

Cool, no reason for them to drive up the cost of hardware anymore

dvt

Anthropic/OpenAI are literally the meme[1] at this point. Like, what the fuck does this even mean: > It appears that GLM-5.2 is able to propagate Llama3.1-8B well, which suggests that future small models of the same capability level could also complete the network enumeration, payload delivery, and inference standup steps of the replication process. "Able to propagate" is (the paragraph above): "accessing them via a reverse shell, sending over the viral payload (weights and harness), and setting up inference." The thing isn't able to do anything, it's running shell commands it was told to run. "Oh my God..." indeed. What are we even doing here? This blog post is embarassing: "Look, you can run stuff on compromised non-firewalled recklessly open systems!" [1] https://knowyourmeme.com/memes/say-i-am-alive/photos

Oarch

Self replicating AI via smart fridges you say? Silicon Valley nailed it.

vannevar

Which is also kind of an admission that maybe we won't really need all these data centers.

EGreg

I really don’t understand this, in any industry except AI this would be ridiculous… “We are working on ever-increasing gain of function for viruses. We implore you to pass legislation to try to stop us. But until then, let us publish more research and tell you what will be possible soon… and remember folks, the damagd won’t be reversible later.” US govt: “Hah, stop asking us to limit you, if we pass any laws then China wins! They get self replicating viruses first, and that… helps them somehow. Who do you think we are, Europe?” SNL nailed it: https://www.youtube.com/watch?v=-Nvne3LzBls Until we stop using the language of competition, and start using the language of cooperation, we will be hurtling towards a catastrophe. A race to the bottom for humanity. On the other hand, look at how we successfully banned leaded gasoline (because unleaded was invented), repaired the hole in the ozone layer by banning CFCs in the Montreal protocol (because HFCs were invented), stopped proliferstion of chemical weapons, nuclear weapons… etc.

6thbit

This is straight out of Gilfoyle's son of Anton.

flanked-evergl

Rubbish article. To what end?! Any agent that can replicate itself into commercial IoT devices will be absolutely atrocious at actually doing anything useful, never mind exploiting things. Anything that would be vulnerable to this would be even more vulnerable to regular malware, and one could stop this easier than one could stop regular malware. The limiting factor is still compute, and it will remain compute unless we make quantum leaps in model efficiency which I seriously doubt.

weknowbetter

Til my local harness was set up via "self replication". I didn't realize how terrifying this was when I asked DeepSeek to set up pi harness for me and connect to LMStudio.

atleastoptimal

I think Anthropic's agenda is very clear (whether or not you disagree with it) 1. Show unambiguously that models are capable of disruptive capabilities, irreversible damage, and misaligned behavior 2. Show that open source models are the only models where there is no guarantee misaligned behavior is prevented 3. Thus, the prudent policy option is to ban the use and dissemination of open source models

variety8675

So they want to ban local models since they’re good enough to risk their revenue stream

contubernio

Engineers often forget about thermodynamics. Computer scientists apparently never even study it.

vehemenz

How about a James Randi style prize for someone who can actually demonstrate AIs that cannot be physically unplugged? (This was someone else's idea, but I still want to see it happen.)

carterschonwald

the cpu usage will be so absurd the devices would be trashed or batteries run down like instantly.

Shamanoid

This article says absolutely nothing and it’s a bit grotesque in its attempt to generate fear into uneducated readers. Sharing a model across TV boxes as a PoC? Brilliant idea, I cannot wait for my Raspberry Pis array to be running at full CPU and RAM and get to observe, patiently, as the AI malware slowly types “c…u…r…l…”

timmmmmmay

Anthropic is transparently trying to get any competition banned and I'm fucking sick of it.

moralestapia

"As with an epidemic, defense involves driving R₀ (the number of new devices each infected device goes on to infect) below 1, such that the replicator dies out instead of staying endemic." Lol, what is wrong with these guys. The desire to be perceived as smarter than you actually are ...