

I’m assuming this is daisy chained. In a power strip there are not cables between the plugs that can be unplugged. Nor are there switches on each individual plug that can be accidentally flipped off. Any extra component is a failure mode. If it gets unplugged it loses power just the same as any failure. Now don’t get me wrong, I think this design is clean, expandable, and offers some neat features over a plain power strip, but to suggest there aren’t extra risks associated with this design is a bit short sighted.







Yeah this is the part about all this AGI talk and AI going rogue, it requires a prompt. It responds to an input. These agentic systems have powerful tools that can do other things then spit out text but it’s always responding to a prompt. It may be in a loop responding to its own prompt but it’s still a prompt. And what it spits out is never really anything new. It’s some derivation of what it’s ingested. Actual human intelligence works differently. We do come up with new ideas, new thoughts. So I’ve often thought these LLMs are a dead end to AGI.