Simon Skade
@simonskade.bsky.social
Trying to make the future go well. AI alignment research; now exploring advocacy. Also hardcore rationality.
First post in my AI alignment sequence is out!
Why would an AI "want" anything? This post explains the structure of goal-directed reasoning, why capable AIs will have it, and why this matters for alignment.
www.lesswrong.com/posts/hDZm59...
Why would an AI "want" anything? This post explains the structure of goal-directed reasoning, why capable AIs will have it, and why this matters for alignment.
www.lesswrong.com/posts/hDZm59...
[Intro to AI Alignment] 1. Goal-Directed Reasoning and Why It Matters — LessWrong
1.1 Summary and Table of Contents
Why would an AI "want" anything? This post answers that question by examining a key part of the structure of intell…
www.lesswrong.com
December 30, 2025 at 4:06 PM
First post in my AI alignment sequence is out!
Why would an AI "want" anything? This post explains the structure of goal-directed reasoning, why capable AIs will have it, and why this matters for alignment.
www.lesswrong.com/posts/hDZm59...
Why would an AI "want" anything? This post explains the structure of goal-directed reasoning, why capable AIs will have it, and why this matters for alignment.
www.lesswrong.com/posts/hDZm59...