🚨 A dev got so frustrated watching his AI agent write 500 lines for a 5-line problem that he built a fix. He named it Ponytail. Named after the guy every team has: long ponytail, oval glasses, been there longer than the version control! The one who looks at your 50-line pull request, says nothing, and replaces it with a single line. Ponytail is a ruleset and plugin that injects this exact mindset into AI coding agents. Before writing anything, the agent now actively looks for a reason not to. The before and after is stark: - Ask a standard agent for a date picker, and it builds a custom wrapper component with a stylesheet. - Ask a Ponytail-equipped agent, and it just writes <input type="date">. The benchmarks against unconstrained models (Haiku, Sonnet, Opus) are impressive: → 80–94% less code generated → 47–77% cheaper execution → 3–6x faster task completion It works across the modern AI stack, with rules and plugins for Cursor, Windsurf, Cline, Copilot, Aider, and Claude Code. The best code is the code you never wrote. 100% free and open-source. repo link below ↓

BEST . COVER . EVER

🚨 A dev got so frustrated watching his AI agent write 500 lines for a 5-line problem that he built a fix. He named it Ponytail. Named after the guy every team has: long ponytail, oval glasses, been there longer than the version control! The one who looks at your 50-line pull request, says nothing, and replaces it with a single line. Ponytail is a ruleset and plugin that injects this exact mindset into AI coding agents. Before writing anything, the agent now actively looks for a reason not to. The before and after is stark: - Ask a standard agent for a date picker, and it builds a custom wrapper component with a stylesheet. - Ask a Ponytail-equipped agent, and it just writes <input type="date">. The benchmarks against unconstrained models (Haiku, Sonnet, Opus) are impressive: → 80–94% less code generated → 47–77% cheaper execution → 3–6x faster task completion It works across the modern AI stack, with rules and plugins for Cursor, Windsurf, Cline, Copilot, Aider, and Claude Code. The best code is the code you never wrote. 100% free and open-source. repo link below ↓

It's absolutely INSANE what you c̶a̶n̶ could do with Claude Fable 5. Fable made this entire video by itself 🤯 Nate only gave it a /goal prompt, went to the gym, and came back to this.

🚨 @Karpathy predicted the power of the "LLM Wiki." Google just formalized it. Meet Open Knowledge Format (OKF): a vendor-neutral standard for giving foundation models the curated context they need. I can genuinely see this replacing Notion, Obsidian, or traditional wikis for developer teams, and the reason comes down to bookkeeping. Traditional wikis fail because humans inevitably abandon the tedious work of updating them. As Andrej Karpathy pointed out recently, LLMs don't get bored. They don't forget to update a cross-reference, and they can touch 15 files in a single pass. OKF standardizes the interoperability layer so agents can actually do that heavy lifting autonomously. Because the format is minimally opinionated, it doesn't dictate what you write, it just dictates how it's structured. You get: → Human-readable documents that live right alongside your code in version control → Cross-links that map out complex entity relationships without needing a graph database → A system that survives moving between different tools and organizations There is no complex compression scheme. No central registry. If you can cat a file, you can read it. If you can git clone a repo, you can deploy it. This is how we stop rebuilding context pipelines from scratch every time a new model drops. Announcement spec file in 🧵↓

Fable 5 just got banned. Meanwhile, Chinese bros keep grinding. They built something ranked second right behind Fable. They’re going to catch up. Build something better than Fable. Then open source it.

Fable isn't the first. Back in 1999, the PowerMac G4 was so powerful that the Department of Defense banned its export for breaching the 1-gigaflop barrier Steve Jobs turned it into an ad.

🚨 Bootcamps are charging $15k just to teach you how to call the OpenAI API. Meanwhile, this open-source curriculum just dropped 435 lessons to help you build AI from the ground up. It spans 20 phases and ~320 hours. But the best part is the philosophy: you don't touch PyTorch until you understand exactly what it’s doing under the hood. Here is the full stack: → Phase 0-2 (Foundations): Linear algebra and probability through code, plus classical ML from scratch. → Phase 3-6 (Deep Learning): Neural networks from first principles. No frameworks. → Phase 7-9 (Architectures): Transformers, Generative AI, and Reinforcement Learning. You implement attention yourself. → Phase 10-11 (LLMs): Build, train, and deploy large language models. → Phase 12-13 (Multimodal): Vision, audio, and MCP server integration. → Phase 14-16 (Agents): 42 lessons on agent engineering, including a custom ReAct loop in ~120 lines of pure Python. → Phase 17-19 (Production): Infra, deployment, observability, and safety. → Phase 20 (Capstones): 17 shippable projects. Every single lesson ships a real artifact: a prompt, a skill, an agent, or an MCP server. You don't just learn AI. You build it by hand.

THE AI BUBBLE WILL POP IF HE TAKES HIS JACKET OFF!

my boss watching me code with Opus now that Fable got banned

🚨 NVIDIA JUST OPEN-SOURCED ONE OF THE MOST IMPORTANT AI UTILITIES OF THE YEAR Right now, developers are downloading third-party "skills" straight off GitHub for their AI agents. But an AI skill is not just a text prompt. It’s executable code that runs with your system privileges. A skill you grab to save ten minutes can read your environment variables, lift your API keys, and quietly send them to an external server. Recent research shows 26.1% of public skills carry vulnerabilities, and over 5% are outright malicious. NVIDIA’s new release, SkillSpector, closes this gap. It’s an Apache 2.0 licensed security scanner that answers one question: is this skill safe to run? Here is how the pipeline works: → You point it at a GitHub link, local folder, or a single SKILL.md file. → Pass 1: A fast static scan flags credential harvesting, prompt injections, and checks live CVE data. → Pass 2: An optional LLM pass evaluates the semantic intent of the code to clear out false positives. At the end, you get a 0 to 100 risk score and a clear verdict: Safe, Caution, or Do Not Install. It currently scans skills for Claude Code, Codex CLI, and Gemini. Worth running before you blindly trust the next agent skill you find online. repo link in 🧵↓

ICYMI, Anthropic quietly dropped 9 FREE Claude Skills tutorials Covering Projects, Excel workflows, browsing in Chrome, file editing, app integrations, task automation, and more! Zero tech background required, so anyone can learn practical AI free and fast. 🧵↓