Top all-time · #18383
Arthur Juliani
Personal blog · awjuliani.medium.comaiphilosophy
Arthur Juliani's personal blog at awjuliani.medium.com covers ai and philosophy. Since 2022, 4 different Hacker News readers have linked it 4 times. It is still writing: the last post was on 2026-08-05, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
HN readers link Arthur Juliani's Medium post on maximum entropy policies in reinforcement learning. One commenter found it useful for explaining the concept to someone asking for an ELI5.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
What Hacker News says?
What is a ELI5 explanation of KL-regularization and entropy maximization to select the policy? Edited: I found this to be useful for explaining maximum entropy https://awjuliani.medium.com/maximum-entropy-policies-in-rei... I think that in chess you take a piece and that increases the value but you have to consider the position (that is how your pieces can move) and that is the entropy. So maximum entropy is taking…
Comment linking /maximum-entropy-policies-in-reinforcement-learning-everyday-life-f5a1cc18d32d
on “Offline Reinforcement Learning for LLM Multi-Step Reasoning”Submitted Sorry e/acc, Accelerationism is Anti-Capitalist to its Core as a story · 5 points
HN discussionSubmitted Large Language Models Don’t “Hallucinate” as a story · 3 points
HN discussionSubmitted Reflections on a year studying “Consciousness and AI” as a story · 1 points
HN discussion