My mind is going. I can feel it, Dave.

AI has a lying problem

AI Alignment

AI Alignment

What will finally enable this?

Lib-right case
for right-wing unity
on porn

DAO Apocalypse

Only way that battles could be won against such a machine
is asymmetrically,
fought with some new kinds of weapons,
ones that do not even involve physical harm at all

Now,
Then

The larger the language models are, quantifiably, the more they’re telling us what we want to hear.

LLMs have a lying problem.

AI has a hunger for power problem