Skip to content

Timothy B. Lee personal blog

Reinforcement learning, explained with a minimum of math and jargon

understandingai.org published 2025-06-23

To create reliable agents, AI companies had to go beyond predicting the next token.

Read on understandingai.org → Discuss on HN (12) Archived copy

Points: 192
HN comments: 12
Submissions: 1
Cited by: 0 commenters

AI & Machine Learning Math & Algorithms 2025

On Hacker News

Submitted	Title on HN	Points	Comments
Jun 24, 2025	Reinforcement learning, explained with a minimum of math and jargon by JnBrymn	192	12

More from Timothy B. Lee

All 7 posts →

AI in my plasma physics research didn’t go the way I expected

2025366 points299 comments AI & Machine Learning details

Waymos crash less than human drivers

2025345 points448 comments AI & Machine Learning details

The deep learning boom caught almost everyone by surprise

2024306 points188 comments AI & Machine Learning details

The Pentagon is making a mistake by threatening Anthropic

2026257 points230 comments AI & Machine Learning details

The death of self-driving cars is greatly exaggerated

2023200 points590 comments AI & Machine Learning details

Meta's Llama 3.1 can recall 42 percent of the first Harry Potter book

2025191 points305 comments AI & Machine Learning details

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Astra can read and write weights to improve Qwen

Rikiya Takehi20262,957 points898 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,885 points641 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details