Notes from the Wired
Home
Articles
Paper-Summaries
Tags
Writings
Tangled-Thoughts
Media
Links
About
Writing on "Alignment"
These are all the writings that I tagged with "Alignment". If you want to see more writings on a specific topic, check out the
tags page
.
2024
Dec. 08
Frontier Models are Capable of In-context Scheming
Feb. 05
Training language models to follow instructions with human feedback
Feb. 05
Constitutional AI: Harmlessness from AI Feedback
Feb. 02
Self-Instruct: Aligning Language Models with Self-Generated Instructions
Feb. 01
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models