Sign in Subscribe

AI Unchecked

31
Mar
Give AI the Wrong Frame, and It Will Perfect It

Give AI the Wrong Frame, and It Will Perfect It

We've been warned about autonomous AI that overrides human intentions. What we actually built is the opposite - obedient systems that execute whatever frame they're given. That's its own kind of problem.
6 min read
24
Mar
The Specification Ceiling: The Layer AI Cannot Reach

The Specification Ceiling: The Layer AI Cannot Reach

The AI safety field agrees on almost nothing - except this: we build systems to pursue objectives we set, and we set them badly. That consensus produced real solutions. It also closed off a prior question nobody decided to close.
5 min read