AI/ML

Every time I exit Plan mode in Claude Code, a hook automatically captures the plan into my Obsidian vault with a clean title, full frontmatter, a summary gen...

OCR model that handles complex tables, forms, handwriting with full layout. - datalab-to/chandra

I have a new laptop—a 128GB M5 MacBook Pro, which early impressions show to be very capable for running good local LLMs. I got frustrated with Activity Monitor and decided …

A complete guide to CLAUDE.md, custom commands, skills, agents, and permissions, and how to set them up properly.

In this video, we look at LiteParse, a new open document parser created by the people at LlamaIndex. This library allows you to pass a variety of different t...

Yogesh Kumar's personal website

Two AI agents, 11,345 receipts, and 1.6 billion tokens to find out what I’ve spent on eggs since 2001.

When you take an agent out of your IDE and put it on a cron job, everything changes. Here's the prompt architecture that separates 'agents are unreliable' from '15 agents running on a schedule that just work.'

Run “uvx rodney –help” Use rodney to load https://www.pcgamer.com/software/kill-the-algorithm-in-your-head-lets-set-up-rss-readers-and-get-news-we-actually-want-in-2026/ When I loaded that page in ...

A performance audit of the March 2026 PCGamer article on RSS readers reveals severe page bloat, with over 82% of network traffic and transferred bytes traced to ad-tech, tracking, and …

CLI tool for interacting with the web

Image source: Bibliothèque nationale de France An Open Letter to Georgetown Students, In Response to Recent Announcements by the University about “Generative AI” Dear students, As you know, in …

In this video, I'll be talking about whether you really need Google Stitch to build great UIs, or whether Verdent plus Claude Opus 4.6 and the Frontend Desig...

What happens when AI agents can design experiments, collect data, and improve — without a human in the loop? Andrej Karpathy joins Sarah Guo on the state of ...

When I proposed rejecting papers with hallucinated references, the support was overwhelming. But the critical voices revealed five argument patterns: from AI hype through TINA rhetoric to nihilism.

#obsidian #customization #tools Thanks for watching, and I hope you enjoyed learning how to customize your Obsidian vault without writing code, using Lean Ob...

I have been watching HomeAssistant’s progress with assist for some time. We previously used Google Home via Nest Minis, and have switched to using fully local assist backed by local first + llama.cpp (previously Ollama). In this post I will share the steps I took to get to where I am today, the decisions I made and why they were the best for my use case specifically. Links to Additional Improvements Here are links to additional improvements posted about in this thread. New Features Security C...

🔥 Join Maker School & get customer #1 guaranteed: https://skool.com/makerschool/about📚 Watch my NEW 2026 Claude Code course: https://www.youtube.com/watch?...

Get started with Descope: Drag & Drop Your Auth! https://descope.plug.dev/AZj86Ml---Opencode remains the best agent I've used, and after almost 8 months from...

Interested in Karpathy's Autoresearch but don't know where to start? We break down what it is, how it's used, how to run it yourself, and then show how I use...

Visit OnDemand: https://app.on-demand.io/auth/signup?refCode=AICODEKING_MI1In this video, I'll be sharing my first impressions of Pony Alpha 2, a new model f...

CLI-Anything: Making ALL Software Agent-Native

Sandbox your LLM coding agents on macOS. Kernel-level enforcement via sandbox-exec — deny-first, composable, zero dependencies.

Scott and Wes are joined by Phil Miller and Theo Ephraim to talk about Varlock, a new approach to environment variables that adds schemas, validation, and se...

Learn how to fine-tune Qwen3.5 LLMs with Unsloth.

Cmux is a revolutionary terminal by Lawrence Chen, built specifically for AI coding agents that gives them the power to control browsers, spawn subagents in ...

The definitive LLM leaderboard — ranking the best AI models including Claude, GPT, Gemini, DeepSeek, Llama, and more across coding, reasoning, math, agentic, and chat benchmarks. Compare LLM rankings, tier lists, and pricing.