Worth a reread, here is a new report from the front:

Our experiments suggest that small AI models may be months away from being capable enough to self-replicate on commercial IoT devices, like smart ovens and off-brand Android TV boxes. A replicator like this would be challenging to shut down, since there’s no centralized point to shut off – though it may be slow (with a doubling time of days). Unlike non-AI malware, it could also figure out unfamiliar devices on its own. In our evals, a 9B model got inference running on 8 of the 9 hardware types we tested.

I am reminded also of those old fairy tales where the witch casts the Prince into a stone, or some other inanimate object, and he is stuck there until…?  Except this time the AI is imprisoning itself, if this were to happen in the non-test world.  Which LLM do you want in your stove?  Can you have more than one?

Told you all it was going to get weird.