Machine Intelligence - 2026
A chronological archive of Machine Intelligence reading list posts.
2026
October 2026
🔗 GitHub - tools4imps/covenant: The Contract layer for Impatient Programming in Elixir
🔗 Recursive Self-Improvement through Multi-Agent Self-Supervision
🔗 The Markdown thing is getting out of hand
🔗 pinterm
🔗 The Emperor Pelican Has No Clothes
🔗 Otto — Your agents. Always on.
🔗 Game Decompilation, Is This Legal?, A Well-Trodden Path
🔗 AI Is a Tool. Using It Well Takes Skill.
🔗 REA: Reverse Engineering for Your Coding Agent
🔗 GitHub - google-research/harness2
🔗 MacParakeet — Local Dictation & Meeting Recording for Mac
🔗 AirDrop, reverse-engineered for a Framework laptop
🔗 Appalled to realise that Iain Banks used an LLM to write The Player of Games
🔗 How AI Is Cracking Open Video Games
🔗 GitHub - dbreunig/nesformer: An NES CPU compiled into the weights of a stock Qwen3.5 model
🔗 Intent
🔗 A Mathematician Reads the AI Future
🔗 The State of Context Engineering
🔗 The Decoherence Trap: When AI slop drowns out the signal in an endless sea of noise
🔗 Attention Is Not What You Need
🔗 Jev models make agents faster. Hooked control planes steal the difference.
🔗 Introducing Playground: If you can think it, you can play it.
🔗 Qwenputer: a fully functioning, deterministic RISC-V CPU inside Qwen3.5
Was this useful?