Machine Intelligence - 2026

🔗 [2609.14858] Dream-RSI: Recursive Self-Improvement through Evolving Worlds

🔗 NobodyWho vs Cactus: On-Device Inference Engine Comparison

🔗 OtoDock/oto-dock: The agentic company OS. The brains of your company, built on Claude Code and Codex, working on your Anthropic and OpenAI subscriptions.

🔗 NeoLabHQ/context-engineering-kit: Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.

🔗 You Know Who Really Hates AI? Insurance Claims Adjusters

🔗 Announcing the Advisory Group on Mathematics and Artificial Intelligence

🔗 Deterministic Core, Non-Deterministic Shell

🔗 Laya — 33ms Multilingual System 1 Decision Engine with Calibrated Probabilities

🔗 Why AI resembles a charismatic religious leader

🔗 DuckDB Just Put a $400K/Year Skill on Your Laptop

🔗 Herdr: the runtime coding agents run on

🔗 How To Write With An LLM

🔗 affaan-m/ECC: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

🔗 Transformer Explainer: LLM Transformer Model Visually Explained

🔗 Introducing System One Models & Jev

🔗 AI 2027: the race ending

🔗 AI Has No Wisdom and Neither Will You

🔗 An ex-OpenAI researcher just deleted language from the LLM...

🔗 King's AI Summit: Workforce Futures

🔗 The Red Queen hypothesis - a new way forward for self-improving AI

🔗 How I Turned My Security Cameras Into an Automatic Bird Identification System with BirdNet-Go

🔗 How to Build a Diffusion Language Model

🔗 Domain-Driven Agents

🔗 The Rise and Fall of Agent Civilizations

🔗 RAG Is Simpler Than You Think

🔗 Patterns and problems in multiagent systems

🔗 The Technium: Without a theory of intelligence

🔗 BrightbeamAI/chap: CHAP, the Collaborative Human Agent Protocol, is a MCP/A2A-compatible runtime for auditable human-agent work: approvals, overrides, handoffs, escalation and verifiable evidence logs.

🔗 The Safest Job from AI may be Writing

🔗 The End of an Era

🔗 AntV Infographic, an infographic generation and rendering framework that brings words to life.

🔗 2026 Unslop AI-Written Fiction Contest Results

🔗 ChatGPT starts blocking direct requests to copy an author's style

🔗 LLMs aren't remotely like compilers or power tools

🔗 [2601.01828] Emergent Introspective Awareness in Large Language Models

🔗 Bureaucracy Was Built for Mute Documents

🔗 Fairly Trained

🔗 Yann LeCun's $1B Bet Against LLMs [Part 1]

🔗 Judge approves a $1.5B Anthropic settlement over books used to train Claude

🔗 A global workspace in language models \ Anthropic

🔗 Latent Space as a New Medium - by Kevin Kelly

🔗 How LLMs Actually Work

🔗 Kimi K3 is competitive with Fable; Kimi K3 + Fable is SoTA.

🔗 AI as Normal Technology

🔗 GitHub - cactus-compute/cactus: Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots. · GitHub

🔗 WorldClaw — Agentic 3D Open-World Generation at Scale

🔗 The AI Productivity Paradox | Silicon Valley Product Group

🔗 $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

🔗 The AI Compass

🔗 Details That Make Interfaces Feel Better

🔗 Rich Sutton on "AI creativity & discovery"

🔗 Carlota Pérez and the AI boom – where are we in the cycle?

🔗 APERTVS

🔗 Martin Scorsese Is Embracing A.I.

🔗 [2510.04950] Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)

🔗 Ben Affleck says the AI company he just sold to Netflix for $600 million will lead to ‘more human work’

🔗 Design Your AI Team | Envelope — Multi-Agent Designer

🔗 LLMs are complicated now – Ian’s Blog

🔗 OpenCV 5 Deep Dive: A New Foundation for Computer Vision

🔗 Is AI Profitable Yet?

🔗 Building Reliable Agentic AI Systems

🔗 The AI backlash is only getting started

🔗 A New Era of Midjourney

🔗 Orchestrating ambient agents with Temporal

🔗 The founder's playbook: Building an AI-native startup

🔗 I Read the Claude Code Source Code. Here's Everything You Can Configure That the Docs Don't Tell You.

🔗 Teaching LLMs new UI tricks

🔗 How LLMs Actually Work

🔗 GitHub - DietrichGebert/ponytail: Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. · GitHub

🔗 SkillOpt: optimising markdown skill files as trainable parameters

🔗 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

🔗 Teaching Claude why Anthropic

🔗 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

🔗 We let four AI agents run radio companies

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

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

🔗 Sign of the future: GPT-5.5

🔗 Mediator.ai

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

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

🔗 Introducing Claude Design by Anthropic Labs Anthropic

🔗 .claude/commands/handoff.md

🔗 Agent Skill Index

🔗 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

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

🔗 llm-wiki · GitHub

🔗 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

🔗 MicroGPT explained interactively

🔗 Giving LLMs a personality is just good engineering

🔗 Why No AI Games?

🔗 Ensue

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

🔗 AddyOsmani.com - Comprehension Debt

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

🔗 Mateusz Jacniacki

🔗 tobi/qmd: Convert web pages to Markdown

🔗 LLM Architecture Gallery

🔗 x.com

🔗 Why No AI Games? - by Frank Lantz

🔗 AI-generated art can’t be copyrighted after Supreme Court declines to review the rule

🔗 How StrongDM’s AI team build serious software without even looking at the code

🔗 Minor Gripe

🔗 CodeSpeak: Software Engineering with AI

🔗 Agentic Engineering Patterns

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

🔗 microgpt

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

🔗 The End of the Office

🔗 The One-Person Unicorn 🦄

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

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

🔗 nickbostrom.com

🔗 This Test Catches AI Cheaters

🔗 I Gave Claude Access To My Pen Plotter

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

🔗 [2602.10177] Towards Autonomous Mathematics Research

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

🔗 Moltbook: AI-native collaborative workspace

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

🔗 The Agentic AI Handbook: Production-Ready Patterns

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

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

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

🔗 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

🔗 steveyegge/beads: Beads

🔗 Divergent creativity in humans and large language models

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

🔗 Structured LLM outputs

🔗 Agent Jido · Agent Jido

🔗 Moltbook (HN Discussion)

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