Open models may complete these steps, so our models have been doing this for quite some time now. Better ban open models, I guess.
Oh, and, does anyone else realise that what that agentic work is basically how you set up a productive VPS from scratch? How is that supposed to be frightening?
Could this be a way to self-DDoS a botnet of IoT devices? Let them use up all resources doing inference for instructions to replicate to the next one forever.
Open models may complete these steps, so our models have been doing this for quite some time now. Better ban open models, I guess.
Oh, and, does anyone else realise that what that agentic work is basically how you set up a productive VPS from scratch? How is that supposed to be frightening?
Interesting how much of our current timeline the show Person of Interest predicted.
When I watched it back in the early 2010s, a lot of it did not feel believable, but we are living in it after only 11 years of the show ending.
The post you actually want to read https://www.anthropic.com/research/self-replicating-ai
> It added that systems should be strengthened to make it harder for such AI agents to spread.
We'll likely need a new name for them if such viral agents become a reality.
"computing lockdown and regulatory capture pretext providers"
Like there is DDR5/HBM elsewhere.
Claude's gonna love my 256mb raspberry pi!
pure anthropic anti open-model propaganda.
Anthropic: "Oh no! Small (open source) models might self-replicate. Better ban those. :^)"
Could this be a way to self-DDoS a botnet of IoT devices? Let them use up all resources doing inference for instructions to replicate to the next one forever.
Oh yes I can totally see a webos TV, that has bugger all storage, hosting a 22B parameter model /s