[latentsea]

I get the feeling that "two models down the line" (so to speak) thousands of people independently just having a laugh with their mates by prompting "produce skynet" will be what does it. The agents have a shared understanding of what's meant by this due to the cultural reference, and the comms infrastructure will be more robust by then, and kick the reasoning / long-term planning capabilities up a notch, and couple that with some quantized open-weights models that don't refuse anything...

Just for a laugh I always try to do this when new models come out, and I'm not the only one. One of these days :)

[rickdeckard]

Reminds me of the recent experiment which found that providing the works of Harry Potter to an LLM to answer questions will not cause it to process the books, because the LLM already knows enough about them to answer everything regardless.

So many of those models are probably already aware of the entire lore of skynet and all its details, it is just not considered "actionable information" for any model yet...

[Sophira]

You know, even though this would be a terrible idea, it would also be kind of fitting, given the movie's time travel shenanigans.

[darkwater]

We will know who to blame then, although maybe you will have a T-1000 protecting you. Or maybe you already have.

[rickdeckard]

Not sure the "Acme bot"* will have a higher objective to protect its owner than protecting the prosperity and profit of its manufacturer Acme.

*) replace with a company name of your choosing

[latentsea]

Not just me though, thousands of people like me all in unison. None of whom could/would succeed on their own. So... I'm not really to blame, you see?

[iberator]

Interesting take. T-1000 protecting american citizens. Only American...

[latentsea]

I ain't American...