π
π
Tag cloud
Picture wall
Daily
RSS Feed
Login
Remember me
631
shaares
631
shaares
Filters
Links per page
20
50
100
Why AI alignment could be hard with modern deep learning
Why would we program AI that wants to harm us? Because we might not know how to do otherwise.
aidk
·
llm
·
research
May 5, 2026 at 9:18:33β―PM EDT * ·
permalink
·
·
https://www.cold-takes.com/why-ai-alignment-could-be-hard-with-modern-deep-learning/
·
Filters
Links per page
20
50
100
Fold
Fold all
Expand
Expand all
Are you sure you want to delete this link?
Are you sure you want to delete this tag?
The personal, minimalist, super fast, database-free, bookmarking service by the Shaarli community
