best skills for youtube transcript scraping? go!

Ill be making a bigger write up here shortly on all this but lots of questions, answers and more questions. Play this in the car, on the way home from work or use it like another lesson!

What a Friday. For two years, if you were building anything serious with AI, you were building on Claude. Not because it was a rule — because it was the right call. Anthropic set the bar for coding. They set the bar for writing. They set the quiet default that if you cared about quality, you paid the Opus premium and didn't ask questions. I didn't either. The whole builder community ran on Claude for a reason. This week, that changed. GPT-5.5 shipped yesterday. DeepSeek V4 Pro shipped the same day. Inside twenty-four hours, the ceiling on agentic coding went up — and the open-weight floor came within striking distance of the closed frontier. Real contenders. Not "almost there." Actually here. Three things this changes for anyone building, and none of them are in the headlines yet. Coding: The default setting of "Claude writes the code, Claude runs the agents" breaks this week. GPT-5.5 is measurably better on the kind of long-running multi-step agent work that used to be Claude's moat. DeepSeek V4 Pro is within a fraction on real software engineering, at a price point where "run it myself" is genuinely on the table. Every tool in your stack that quietly assumed Anthropic — your IDE integrations, your review agents, your automation glue — is about to get reconsidered. That's good for you. Less lock-in. More leverage. Marketing and writing: The price-per-draft math just flipped. We've been rationing the good model forever — the flagship handles the brand-safe stuff, volume work gets the cheap model, and we've all quietly accepted that frontier-quality writing at scale isn't possible. That's over. Frontier-quality writing at open-weight pricing means every ad variant, every email rewrite, every landing-page test, every personalization loop runs at the top tier. The whole architecture of "one good draft, fifty cheap copies" starts feeling as dated as shared creative. Everything top-tier. Everything personalized. Everything testable. Agentic work: This is the one I am most excited about, and the most under-talked-about. For two years, "multi-model agent stacks" has been a slide in decks. Nobody actually builds them, because there hasn't been a real second option. GPT-5.5 for the reasoning step. DeepSeek V4 Pro for the long-context research step. Claude for the interpretive writing step. A cheap open model for the high-volume structured step. Not one runtime. A pipeline. Composed by you. Owned by you. That stops being a slide and starts being the default next month.

Consider this a thank you @Jake Van Clief for the inspiration and giving us the mindset and tools to grow our businesses. ***Disclaimer: this is an advanced setup. DONOT use until you're fully comfortable with Jake's method*** =============================== Many of us eventually hit the limit with basic chat interfaces. The agent forgets context between sessions, data security starts to feel risky, and the setup creates more friction than value. This stack addresses those issues directly It combines Hermes Agent with Cognee as the memory engine, hosted on a simple DigitalOcean Droplet and secured through Cloudflare Tunnel. The entire deployment follows Jake Van Clief’s Interpretable Context Methodology for clean, repeatable orchestration. The result is a private, self-improving AI agent that grows more capable over time while keeping your data and server fully under your control. The components stay minimal and transparent: Hermes Agent as the autonomous gateway, Cognee for structured relational memory, and Cloudflare Tunnel for secure outbound-only access. You deploy once using the ICM workflow, then the system handles the repetitive memory management and self-improvement loops. The agent becomes a genuine thinking partner instead of a one-off responder. That frees up your attention for the judgment and creative work only you can do. If you are running a self-hosted agent setup or exploring similar private stacks, I would like to hear what you are using and what friction you have solved. Drop your thoughts below.

Quick version in case you missed it: instead of using RAG to re-chunk your sources every time you ask a question, you compile each source once into a persistent markdown wiki. The LLM extracts concepts, writes entity and concept pages, updates cross-references, flags contradictions, and maintains the whole thing. Future queries read the pre-synthesized wiki. The part that clicked for me: the reason most of us abandon our second brains is that backlink and cross-reference upkeep is boring. The LLM doesn't care. It's happy to touch fifteen pages in one pass. I spent a couple of weeks turning Karpathy's pattern into a Claude Code plugin that actually scales (atomic pages, sharded indexes, BM25 fallback past ~300 pages). It also runs in Codex, Cursor, Gemini CLI, Pi, and OpenClaw through the skills CLI. Install in Claude Code: /plugin marketplace add praneybehl/llm-wiki-plugin /plugin install llm-wiki@llm-wiki Or in any other supported agent: npx skills add praneybehl/llm-wiki-plugin -a <your-agent> Five slash commands (init, ingest, query, lint, stats), stdlib-only Python, no dependencies. Plays well with Obsidian if you want the graph view. Repo: https://github.com/praneybehl/llm-wiki-plugin Karpathy's gist: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f Curious if anyone here has tried the pattern themselves. What did you ingest first, and what broke before it worked?