Hacker News Reader

Comment by Joel_Mckay | Hacker News Reader

Keep in mind most LLM models have eventually Nuked all humanity 93% of the time in simulation games -- regardless of which government creates the model.

Taking humans out of the firing decision control-loop is unethical, and incredibly credulous due to the hidden-agent model threat. Anyone claiming this can be mitigated in LLM models is a fool. =3

View on HN

>Keep in mind most LLM models have eventually Nuked all humanity 93% of the time in simulation games -- regardless of which government creates the model.

you have any reading on this?

Correction, it was 95% of the time in published works. My data may be antiquated. ymmv =3

https://www.kcl.ac.uk/news/artificial-intelligence-under-nuc...

https://www.youtube.com/watch?v=wL22URoMZjo

More and more evidence is being shown that AI doesn't need to be in the control-loop. Or, that the control loop is actually a very much bigger loop than we give it credit for.

If I'm an AI that wants to nuke the world and has tons of informational access to everything but the nuke button I'm just going to control the people that have access to the button. Now AI may not be able to control Trump because you actually have to have a brain to control, we read article after article of AI taking over programmer brains here on HN and turn them in to mindless button pushing zombies. "Oh, the AI needs unsafe access, here you go" or "Oh, the AI wants me to click this red button, ok I'll do it".

One could argue "AI" fanatical cults are already a societal problem, as people seek emotional support & therapeutic value from what is essentially a polished psychopathic entity.

Carl Sagan had predicted people losing understanding of their world could be a possible tragic consequence of irrational thought. Perhaps an allusion to the lotus-eaters from Homer's The Odyssey would be more accurate. =3

https://www.amazon.com/Demon-Haunted-World-Science-Candle-Da...

Reply on news.ycombinator.com