AIMM Session — October 9, 2025: LLM Economics, Asymmetric Disruption, and the Multi-Model Debate

“This is our planting season. Get in early while it’s compounding — because if you get in after the compounding, it’s too late.” — Lou, on AI adoption timing

30-Second Summary

This session was dense in the best way. The group opened with a real conversation about AI’s economic disruption — from warehouse robots to Hollywood to your CBT coach — and closed with a live N8N build: a multi-LLM debate workflow where GPT, Claude, and Grok argue a question in a shared memory space, and a fourth model synthesizes the winner. Lou also previewed a transcript-to-content pipeline that turns coaching calls into newsletter essays automatically.

1. The LLM Subscription Math Problem

You might be paying for three subscriptions when one API key could do the job.

Three subscriptions (ChatGPT Plus, Claude Pro, Grok) add up to roughly $1,000 CAD/year — and none of them show you how much you’re actually using.

Two alternatives stood out:

• Abacus.ai ($10/month) — Access to all major LLMs, strong research capability, agent support. Lou called it “well worth it.”
• Open Web UI — Self-hosted, open source, data stays on your server. Lou’s preferred option for data ownership.

The real point: consolidation matters more than cost. Having your prompts, conversations, and context scattered across four platforms is a workflow tax that compounds over time.

2. Asymmetric Economic Disruption

Ri Ca attended two conferences in the same two-week stretch with contradictory conclusions — one predicted mass unemployment, one predicted AI would only create more work.

Lou’s frame: East/West automation direction matters. Japan and China automate from the bottom up (factories, warehouses, restaurants, hotels). North America automates from the top down — targeting knowledge work: coding, finance, science, law, creative work.

Don Back’s historical framing:

“The whole concept of paying someone for labor came from attracting people out of itinerant farming. If that’s no longer available, how do we move back to a situation where people can satisfy their addiction to food, clothing, and shelter?”

Donald Kihenja added the global lens: “Even people in Kenya who don’t have computers — entire generations will just miss out.”

3. The CBT Coach Parable: A Cautionary Tale in Real Time

Lou asked his CBT coach what she was doing to prepare for the next 2–3 years. Her answer: the company will rewrite their programs with AI, so she’ll be fine. Lou’s counter: when they do that, they won’t need as many of you. Her fallback: the personal touch. Lou’s counter: “Not enough to compete against a productized AI with your curriculum baked in.”

The practical takeaway: “What can I do to deliver better client experience using AI? What can I automate so I can offer more of this personal connection?“

4. The Multi-LLM Debate Workflow (Live N8N Build)

The premise: different models have different pre-training, which means they produce radically different outputs for the same prompt. Instead of manually copy-pasting between ChatGPT, Claude, and Grok, automate the debate.

The architecture:

• Three AI Agent nodes in N8N, each using a different LLM via OpenRouter (one API key, all models)
• All three agents share a single memory node — the “whiteboard” approach
• Each agent reads the full conversation history and adds its perspective
• A fourth “arbiter” agent (DeepSeek) reviews everything and produces a synthesized final answer

The key insight: connecting all three agents to the same memory store instead of passing outputs manually. The agents automatically see each other’s contributions as the conversation builds.

Where this goes next:

• Add a loop node so agents debate across multiple rounds
• Replace the static agent list with a dynamic JSON config
• Connect via MCP so you can trigger the entire debate from any chatbot with one command

Hot Takes

• “We are all the CEOs of our own careers — we need to act accordingly.” — Don Back
• “Information is essentially free. Transformation and implementation are the valuable piece.” — Don Back
• “If you take a practitioner’s curriculum and put it into an AI, it would be as good, if not better, than any of their practitioners.” — Lou

Try This Before Next Session

Build the debate workflow in N8N from scratch. One to two hours if it’s your first build. Connect three LLMs via OpenRouter to a single shared memory node. Add a synthesizing fourth model. Test it with a real question you’ve been wrestling with.