Machine Intelligence - 2026
A chronological archive of Machine Intelligence reading list posts.
2026
March 2026
🔗 Ensue
🔗 microgpt
🔗 MicroGPT explained interactively
🔗 Why No AI Games? - by Frank Lantz
🔗 How I run 4–8 parallel coding agents with tmux and Markdown specs — Manuel Schipper
🔗 Agentic Engineering Patterns
🔗 How StrongDM’s AI team build serious software without even looking at the code
🔗 AI-generated art can’t be copyrighted after Supreme Court declines to review the rule
🔗 Giving LLMs a personality is just good engineering
🔗 GitHub - msitarzewski/agency-agents: A complete AI agency at your fingertips
🔗 CodeSpeak: Software Engineering with AI
🔗 Exclusive: Anthropic ‘Mythos’ AI model representing ‘step change’ in power revealed in data leak
🔗 AddyOsmani.com - Comprehension Debt
🔗 Persona vectors: Monitoring and controlling character traits in language models Anthropic
February 2026
🔗 I Gave Claude Access To My Pen Plotter
🔗 This Test Catches AI Cheaters
🔗 The 5 Levels of AI Coding (Why Most of You Won't Make It Past Level 2)
🔗 GitHub - stablyai/agent-slack: Slack automation CLI for AI agents
🔗 data_engineering_book/README_en.md at main · datascale-ai/data_engineering_book · GitHub
January 2026
🔗 The Executive Assistant Paradox: Why AI Makes This Role More Critical, Not Obsolete
🔗 Today's organisations don't have an AI problem — they have a thinking problem
🔗 Divergent creativity in humans and large language models
🔗 KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
🔗 Letting Claude Play Text Adventures
🔗 parcadei/llm-tldr: 95% token savings, 155x faster queries for LLM codebase analysis
🔗 The Agentic AI Handbook: Production-Ready Patterns
🔗 steveyegge/gastown: Gas Town - multi-agent workspace manager
🔗 parcadei/Continuous-Claude-v3: Context management for Claude Code
🔗 Moltbook: AI-native collaborative workspace
🔗 Building an internal agent: Code-driven vs LLM-driven workflows
🔗 king - man + woman is queen; but why?
🔗 Impeccable: The missing upgrade to Anthropic's frontend-design skill
🔗 Towards a science of scaling agent systems: When and why agent systems work
Was this useful?