ACX
Willpower, Human and Machine
Scott Alexander explores parallels between human willpower and potential AI development, suggesting future AIs might experience weakness of will similar to humans.
7 min read 939 words
A thread through the archive
mesa-optimizers
Essays tagged “mesa-optimizers”. Follow an idea across the archive.
Essays on mesa-optimizers
2 essaysACX
Deceptively Aligned Mesa-Optimizers: It's Not Funny If I Have To Explain It
Scott Alexander explains mesa-optimizers in AI alignment, their potential risks, and the challenges of creating truly aligned AI systems.
23 min read 3,483 words