Machine Intelligence - 2026

🔗 Wiki Builder: a Claude Code plugin for agentic engineering wikis

🔗 SkillOpt: optimising markdown skill files as trainable parameters

🔗 20 Concepts to Understand AI in 2026

🔗 Andrej Karpathy: From Vibe Coding to Agentic Engineering

🔗 GitHub - MinishLab/semble: Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read · GitHub

🔗 GitHub - SillyTavern/SillyTavern: LLM Frontend for Power Users · GitHub

🔗 How much electricity does AI consume? [2025 summary]

🔗 Vibe coding and agentic engineering are getting closer than I’d like

🔗 A Theory of Deep Learning

🔗 Teaching Claude why Anthropic

🔗 We let four AI agents run radio companies

🔗 GitHub - MeisnerDan/mission-control: Open-source task management for the agentic era. The command center for solo entrepreneurs who delegate work to AI agents. · GitHub

🔗 GitHub - disler/indydevtools: An opinionated, Agentic Engineering toolbox powered by LLM Agents · GitHub

🔗 Mediator.ai

🔗 Running Google Gemma 4 Locally With LM Studio’s New Headless CLI & Claude Code

🔗 Sign of the future: GPT-5.5

🔗 Low-Hanging LLM Fruit for Better Agentic Coding from Frontier Models

🔗 Taste in the age of LLMs

🔗 [2505.13453] Pel, A Programming Language for Orchestrating AI Agents

🔗 Cognitive surrender: Wharton names the thing we're all doing with our AI

🔗 GitHub - brendanhogan/loophole: Adversarial moral-legal code system · GitHub

🔗 GitHub - addyosmani/agent-skills: Production-grade engineering skills for AI coding agents. · GitHub

🔗 GitHub - drona23/claude-token-efficient: One CLAUDE.md file. Keeps Claude responses terse. Reduces output verbosity on heavy workflows. Drop-in, no code changes. · GitHub

🔗 GitHub - MeisnerDan/mission-control: Open-source task management for the agentic era. The command center for solo entrepreneurs who delegate work to AI agents. · GitHub

🔗 .claude/commands/handoff.md

🔗 GitHub - jundot/omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar · GitHub

🔗 Emotion concepts and their function in a large language model Anthropic

🔗 llm-wiki · GitHub

🔗 Introducing Claude Design by Anthropic Labs Anthropic

🔗 The coding-agent Cambrian: six new frameworks, and the paper that explains why they all look alike

🔗 What Science Fiction Can Teach Us About Taste

🔗 GitHub - garrytan/gstack: Garry Tan's Claude Code setup with 23 opinionated tools · GitHub

🔗 tobi/qmd: Convert web pages to Markdown

🔗 Ensue

🔗 Giving LLMs a personality is just good engineering

🔗 Why No AI Games?

🔗 MicroGPT explained interactively

🔗 matthewsinclair/microgptex: A pure-functional Elixir version of MicroGPT

🔗 Exclusive: Anthropic ‘Mythos’ AI model representing ‘step change’ in power revealed in data leak

🔗 Why No AI Games? - by Frank Lantz

🔗 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

🔗 Minor Gripe

🔗 CodeSpeak: Software Engineering with AI

🔗 Mateusz Jacniacki

🔗 x.com

🔗 LLM Architecture Gallery

🔗 Agentic Engineering Patterns

🔗 GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automatically · GitHub

🔗 microgpt

🔗 How I run 4–8 parallel coding agents with tmux and Markdown specs — Manuel Schipper

🔗 GitHub - msitarzewski/agency-agents: A complete AI agency at your fingertips

🔗 The 5 Levels of AI Coding (Why Most of You Won't Make It Past Level 2)

🔗 data_engineering_book/README_en.md at main · datascale-ai/data_engineering_book · GitHub

🔗 The End of the Office

🔗 The One-Person Unicorn 🦄

🔗 nickbostrom.com

🔗 I Gave Claude Access To My Pen Plotter

🔗 This Test Catches AI Cheaters

🔗 GitHub - stablyai/agent-slack: Slack automation CLI for AI agents

🔗 [2602.10177] Towards Autonomous Mathematics Research

🔗 Building an internal agent: Code-driven vs LLM-driven workflows

🔗 The Agentic AI Handbook: Production-Ready Patterns

🔗 Moltbook: AI-native collaborative workspace

🔗 KGGen: Extracting Knowledge Graphs from Plain Text with Language Models

🔗 The Executive Assistant Paradox: Why AI Makes This Role More Critical, Not Obsolete

🔗 Letting Claude Play Text Adventures

🔗 parcadei/llm-tldr: 95% token savings, 155x faster queries for LLM codebase analysis

🔗 parcadei/Continuous-Claude-v3: Context management for Claude Code

🔗 Building internal agents

🔗 Today's organisations don't have an AI problem — they have a thinking problem

🔗 king - man + woman is queen; but why?

🔗 steveyegge/beads: Beads

🔗 Divergent creativity in humans and large language models

🔗 Towards a science of scaling agent systems: When and why agent systems work

🔗 Impeccable: The missing upgrade to Anthropic's frontend-design skill

🔗 Structured LLM outputs

🔗 Agent Jido · Agent Jido

🔗 Moltbook (HN Discussion)

🔗 steveyegge/gastown: Gas Town - multi-agent workspace manager