AI/ML

Browse 25,000+ agent skills compatible with Claude Code, Codex CLI and ChatGPT. The open standard SKILL.md format for AI coding assistants.

We spent months building a sophisticated text-to-sql agent, but as it turns out, sometimes simpler is better. Giving it the ability to execute arbitrary bash commands outperformed everything we built. We call this a file system agent.

A small pansharpening model

Best OCR and vision language models you can run locally that transform documents, tables, and diagrams into flawless markdown copies with benchmark-crushing accuracy.

My startup for terminals wrapped up mid-2025 when the funding ran dry. So I don’t have money, but what I do have are a very particular set of skills. Skills I have acquired over a very long career convincing terminals they are actually GUIs.

Contribute to Tencent-Hunyuan/AutoCodeBenchmark development by creating an account on GitHub.

A far more detailed explanation of prompt caching than anyone asked for.

Sam Rose is one of my favorite authors of explorable interactive explanations - here's his previous collection. Sam joined ngrok in September as a developer educator. Here's his first big …

I’ve been having an absurd amount of fun recently using LLMs for cooking. I started out using them for basic recipes, but as I’ve grown more confident in their culinary …

How do four modern LLMs do at recreating a simple Windows gaming classic?

kagi Prompt

What you need to know about local model tooling and the steps for setting one up yourself

With GPT-5, Claude 4.5 Opus, Gemini 3.0 Pro and so many more, it's been a wild year.Thank you WorkOS for sponsoring! Check them out at: https://soydev.link/w...

I tested PaddleOCR, Tesseract, EasyOCR, GPT-4o, and Mistral OCR 3 on handwritten notes. See which handles cursive and messy text. Real benchmark results.

Independent ML benchmark tracking. Compare models with verified data, practical recommendations, and open datasets.

85.7% live with unresolved AI tensions. Creatives struggle most yet adopt fastest. A deep analysis.

2025 Year in Review of LLM paradigm changes

Every M3 Ultra Mac Studio and Mac Mini cluster I’ve built hit the same wall… until Apple quietly removed the bottleneck—and suddenly, we're running the real deal. 👀 Start learning cyber security with TryHackMe: https://tryhackme.com/ziskind Use my code "ZISKIND25" to get 25% off on annual subscription! 🛒 Gear Links 🛒 ⌨️🏢 The rack in this video: tall version- https://amzn.to/4cvsfk3 short version - https://amzn.to/4j6Nuv4 🪛🪛Highly rated precision driver kit: https://amzn.to/4fkMVfg 💻☕ Favorite 15" display with magnet: https://amzn.to/3zD1DhQ 🎧⚡ Great 40Gbps T4 enclosure: https://amzn.to/3JNwBGW 🛠️🚀 My nvme ssd: https://amzn.to/3YLEySo 📦🎮 My gear: https://www.amazon.com/shop/alexziskind 🎥 Related Videos 🎥 🧳🧰 Mini PC portable setup - https://youtu.be/4RYmsrarOSw 🍎💻 Dev setup on Mac - https://youtu.be/KiKUN4i1SeU 💸🧠 Cheap mini runs a 70B LLM 🤯 - https://youtu.be/xyKEQjUzfAk 🧪🔥 RAM torture test on Mac - https://youtu.be/l3zIwPgan7M 🍏⚡ FREE Local LLMs on Apple Silicon | FAST! - https://youtu.be/bp2eev21Qfo 🧠📉 REALITY vs Apple’s Memory Claims | vs RTX4090m - https://youtu.be/fdvzQAWXU7A 🧬🐍 Set up Conda - https://youtu.be/2Acht_5_HTo ⚡💥 Thunderbolt 5 BREAKS Apple’s Upcharge - https://youtu.be/nHqrvxcRc7o 🧠🚀 INSANE Machine Learning on Neural Engine - https://youtu.be/Y2FOUg_jo7k 🧱🖥️ Mac Mini Cluster - https://youtu.be/GBR6pHZ68Ho * 🛠️ Developer productivity Playlist - https://www.youtube.com/playlist?list=PLPwbI_iIX3aQCRdFGM7j4TY_7STfv2aXX 🔗 AI for Coding Playlist: 📚 - https://www.youtube.com/playlist?list=PLPwbI_iIX3aSlUmRtYPfbQHt4n0YaX0qw EXO Github repo: https://github.com/exo-explore/exo Awni's MLX dist setup Gist: https://gist.github.com/awni/ec071fd27940698edd14a4191855bba6 My extra script (don't just run these, they need work, so be careful. They are just there for guidance): https://github.com/alexziskind1/mlx-dist-setup — — — — — — — — — ❤️ SUBSCRIBE TO MY YOUTUBE CHANNEL 📺 Click here to subscribe: https://www.youtube.com/@AZisk?sub_confirmation=1 — — — — — — — — — Join this channel to get access to perks: https://www.youtube.com/channel/UCajiMK_CY9icRhLepS8_3ug/join — — — — — — — — — 📱 ALEX on X: https://x.com/digitalix 📱 AWNI (MLX) on X: https://x.com/awnihannun #macstudio #m4max #m3ultra

This AI leaderboard shows comparison of capabilities, price and context window for leading commercial and open-source LLMs, based on the benchmark data provided in technical reports in 2025.

Comparison of API provider performance across over 500 AI Model endpoints, including from OpenAI, Google, DeepSeek and others, across performance key metrics including price, output speed, latency, context window and more.

The IDP Leaderboard is a unified benchmark for document understanding tasks, including OCR, KIE, classification, question answering, table extraction, and confidence score evaluation.

OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning

#1 OpenCode Plugin- Battery included. ASYNC SUBAGENTS (YES LIKE CLAUDE CODE) · Curated agents with proper models · Crafted tools like LSP/AST included · Curated MCPs · Claude Code Compatible Layer ...

On the topic of artificial intelligence, like far too many topics these days, it seems that the vast majority of opinions out there are highly polarized. Either you’re all about making fun of…

Join the AI Evals Course starting Jan 27, 2026: https://maven.com/parlance-labs/evals?promoCode=tf-yt-c4Watch Shreya Shankar and I break down five years of g...

Create better AI-prototyping designs by using precise visual keywords, references, analysis, as well as mock data and code snippets.

I recently came across JustHTML, a new Python library for parsing HTML released by Emil Stenström. It’s a very interesting piece of software, both as a useful library and as …