Tsinghua's Multi-Agent AI Classroom, Anthropic's Context Engineering Playbook, and a 54 LLM-Architecture Gallery - 📚 The Tokenizer Edition…

This week's most valuable AI resources

Apr 2 • Sairam Sundaresan

13

March 2026

Google Compresses KV-Cache 6x Without Training, How Every Modern Attention Variant Works, and a Claude Code Cheat Sheet - 📚 The Tokenizer…

This week's most valuable AI resources

Mar 26 • Sairam Sundaresan

12

2

Claude Code Best Practices, Planning in 8 Tokens, and Why Reasoning Models Can't Control Their Own Thoughts - 📚 The Tokenizer Edition #20

This week's most valuable resources

Mar 18 • Sairam Sundaresan

17

2

Karpathy's Autonomous ML Lab, Sleeper Cells in LLMs, and Andrew Ng's Context Hub - 📚 The Tokenizer Edition #19

This week's most valuable AI resources

Mar 11 • Sairam Sundaresan

16

February 2026

Accio Insights: The Marauder’s Map of the ML World

A deep dive into the swiss army knife of machine learning

Published on The Palindrome • Feb 25

Karpathy's microGPT, Jeff Dean's Pareto Frontier, and the LLM Course - 📚 The Tokenizer Edition #18

This week's most valuable AI resources

Feb 19 • Sairam Sundaresan

15

Google's Viral Paper Banana, How to Systemize Claude Code, and Stanford on Agents & RAG - 📚 The Tokenizer Edition #17

This week's most valuable AI resources

Feb 11 • Sairam Sundaresan

13

2

DeepSeek's Human-Like Vision, Chip Huyen's AI Tools Site, and Stanford's Updated LLM Course - 📚 The Tokenizer Edition #16

This week's most valuable AI resources

Feb 3 • Sairam Sundaresan

18

1

January 2026

Tencent Compresses Reasoning 3-4x, Robots Master 35,000 Hours of Human Data, and Anthropic's Evaluation Framework - 📚 The Tokenizer Edition…

This week's most valuable AI resources

Jan 26 • Sairam Sundaresan

7

3

2

NVIDIA Fixes Multi-Reward RL Collapse, Video Agents Lose Their Train of Thought, and LLM Benchmarks That Judge Themselves - 📚 The Tokenizer…

This week's most valuable AI resources

Jan 19 • Sairam Sundaresan

8

2

2

The Last Mile is Always Human

What's next for Gradient Ascent (looking back and ahead)

Jan 4 • Sairam Sundaresan

15

2

2

December 2025

Andrew Ng on Navigating AI Careers, DeepMind CEO on Gemini 3, and Microsoft's Agent Curriculum: The Tokenizer Edition #13

This week's most valuable AI resources

Dec 20, 2025 • Sairam Sundaresan

10

1

1