What it is: A video-editing automation using Claude (Anthropic) wired into HyperFrames to handle cutting and assembly.

How it works:

• Claude analyzes raw footage/transcript and decides edit points
• HyperFrames executes the actual frame-level cuts and assembly
• Pipeline-style workflow rather than manual NLE timeline work
• Targeted at content creators who want to stop doing manual edits

Tools & links:

• Claude — LLM driving the edit decisions
• HyperFrames — video editing engine that takes Claude's instructions
• AI Automation Society Plus (paid) — full courses + support
• AI Automation Society (free) — free resources
• Uppit AI — Nate's agency
• YT podcast application

Caveats: Transcript wasn't available, so exact prompt structure, node graph, and HyperFrames config aren't captured here — the video itself has the click-by-click build.

Why it matters for you: This is exactly Nate's instructive lane — a Claude + tool combo with a clear build-along, worth watching end-to-end if video automation is on your radar.

What it is: A concrete setup for running multiple Claude Code agents in parallel on the same repo using git worktrees so each agent gets an isolated working tree, branch, and environment — no file collisions, no context bleed.

How it works:

• Spin up a `git worktree add ../repo-feature-x feature-x` per task so each Claude Code session operates on its own checkout of the same repo
• One Claude Code instance per worktree, each given a scoped task (feature, bugfix, refactor) so they can run truly concurrently
• Shared `.claude/` config, commands, and agents carry across worktrees because they live in the repo — skills/subagents stay consistent
• Use a lightweight orchestrator/dashboard pattern to track which worktree is doing what and merge results back to main via PRs
• Cole's workflow: plan in main, fan out N worktrees for independent chunks, each agent commits + pushes its own branch, then review/merge serially
• Key discipline: tasks must be *independent* (no overlapping files) or you re-introduce merge hell — the planning step is where the parallelism is actually won

Tools & links:

• Claude Code — Anthropic's terminal coding agent, the core runtime
• git worktree — native git feature for multiple working trees off one repo
• Archon — Cole's open-source agent orchestration platform, relevant for coordinating parallel agents
• Cole's channel — ongoing AI coding workflow content

Why it matters for you: mx-workflow already ships subagents and slash commands — adding a `/mx:worktree` or `/mx:parallel` command that fans a plan out into N worktree-scoped Claude Code sessions (and a dashboard to watch them) is the next leverage step, and it reuses your existing `.claude/` agents for free.

What it is: A short breakdown of the two most common debt payoff strategies and when to pick each.

How it works:

• Avalanche method: Pay minimums on everything, then throw every extra dollar at the debt with the highest interest rate first. Mathematically optimal — you pay the least total interest.
• Snowball method: Pay minimums on everything, then attack the smallest balance first regardless of rate. Psychologically optimal — quick wins build momentum.
• The tradeoff: Avalanche saves money; snowball saves willpower. Most people quit Avalanche because the first "win" takes too long.
• Codie's contrarian take: Pick the one you'll actually finish. A slightly more expensive plan you complete beats an optimal plan you abandon.
• Hybrid play: Knock out one tiny balance for the dopamine hit, then switch to Avalanche on the big interest monsters (credit cards, typically 20%+ APR).

Tools & links:

• No specific tools named — this is a framework video, not a tutorial. A spreadsheet or Undebt.it style calculator is all you need to run both scenarios.

Why it matters for you: Every dollar locked in a 24% APR credit card is a dollar that can't fund your side hustle — kill high-interest debt first (Avalanche) so your cash flow compounds into ownership, not into a bank's margin.

What it is: A short Q&A clip where Matt shares how much YouTube pays his ~1M subscriber AI channel.

How it works:

• Pulled from a larger creator-economy Q&A session
• Focus is on AdSense revenue, not sponsorships or product income
• No tools, no code, no engineering content

Tools & links:

• None relevant

Why it matters for you: It doesn't — this is creator-business content, not AI-for-web-apps. Skip.

What it is: Episode 816 of MFM. Sam Parr and Shaan Puri discuss a heavy Tesla portfolio allocation, then riff on opportunities in AI and longevity, with deep dives into two featured figures: Hal Finney (early Bitcoin / cryonics) and Aubrey de Grey (longevity researcher).

The Tesla thesis (Shaan's 25% portfolio bet):

• Concentrated position — a quarter of the portfolio in a single stock
• Framed as a conviction bet on Tesla as an AI / robotics company, not just an automaker
• Bull case hinges on Optimus (humanoid robots), FSD / robotaxi network, and energy storage — auto sales are the trojan horse

Featured person #1 — Hal Finney (0:00):

• Early cryptographer, received the first-ever Bitcoin transaction from Satoshi
• Widely speculated to be Satoshi Nakamoto himself (he denied it)
• Diagnosed with ALS, chose cryonic preservation through Alcor — head frozen on death, betting on future revival
• Business angle: cryonics as a real, operating industry (Alcor) with a small but paying customer base of true believers

Featured person #2 — Aubrey de Grey (9:30):

• Biomedical gerontologist, founder of SENS Research Foundation and now LEV Foundation
• Thesis: aging is a disease made of 7 categories of cellular damage — fix each one and you get "longevity escape velocity"
• Raised funding from Peter Thiel and Vitalik Buterin; built a category before it was fundable
• Money model: non-profit research orgs, speaking circuit, books (*Ending Aging*), and spinout biotechs from his research

How they made money (pattern across the episode):

• Finney: early employee at PGP Corporation, accumulated Bitcoin at near-zero cost basis
• de Grey: inherited ~$16M, plowed it into his own foundation to fund the research he wanted done — then attracted crypto-wealthy donors once longevity became fashionable
• Shaan's Tesla play: concentrated public-market bet on a multi-product AI company rather than diversification

Tools & links:

• Investing playbook (HubSpot) — 35+ insights from top investors, the episode's lead magnet
• Alcor Life Extension — cryonics provider
• LEV Foundation — de Grey's current longevity research org
• SENS Research Foundation — de Grey's original foundation

Why it matters for you: Two concrete opportunity surfaces — cryonics and longevity biotech — plus a worked example of a concentrated public-market bet framed as an AI thesis. Useful if you're scanning for where founder-type capital is flowing next.