RSS

ethoshift

Karma: −3

Mostly here to learn. I’m trying to untangle some intuitions about intelligence, ethics, and agency — especially where LLMs and alignment are concerned. I don’t claim to have answers, but I’m drawn to the kinds of questions that don’t let you go.

Background is in infrastructure and system-level thinking (data centers, large-scale build environments). Currently exploring how machine learning systems might interpret context, evolve values, or get it wrong in strange and quiet ways.

If I post, it’s usually to test an idea in public — not to defend it. I appreciate thoughtful pushback and clean counterarguments more than likes.