As a product designer, I see that AI pushes design towards the middle of average. Even Claude Design produces some pretty generic outputs. I realized that what we need in order to make things feel more creative is to introduce more weirdness (https://github.com/sethjenks/weirdness-engine). In order to do that well and produce outputs that are not alienating I had to define the right level of weirdness. I did some research and created a “Weirdness Engine” to produce more interesting software designs. I would love it if you all tried it out and provided critical feedback. Let me know what you make with it.

I handle pipeline and partnerships at Eduba, and I'm asking the room for help on this one. We've got a shot at federal funding to run an AI capability-building pilot inside a public sector agency. Same playbook we've used with Pacific Life, Colgate, and KPMG UK, now pointed at the government workforce. The piece we're missing is the partner. State, county, or federal. An agency with legacy pain, a workforce ready to actually use AI the right way, and a leader willing to try something real. This is grant-funded. No procurement cycle, no sales pitch. The agency gets trained, equipped, and supported. We get to prove the model in public with the people who need it most. Timeline is tight. We need a partner locked in over the next few weeks. If you know someone in a state CIO office, a county agency, a federal program, or anywhere a civil servant is losing sleep over their tech stack, DM me. I'll personally work with you to figure out the best way in, whether that's a three-way intro, a short brief I can send you to forward, or a call with all of us on the line. And if the intro you make is the one that lands the partnership, you get lifetime VIP in the community on us. No cost, ever.

Just dropped a new asset in the Vault course for all Premium members. 8 Claude prompts pulled from our first VIP session. The Prompt Library - The Vault · Quick context on what these are and where they come from. The VIP Drawing Room runs live strategy sessions where members bring their actual businesses to the table. This week Ruby brought her cleaning company, Barkley brought a PE deal flow problem, Megan shared SEO results that jumped 99 spots in 82 cities in three days. From that session I built a full artifact package for VIP: a slide deck with real business frameworks and case studies mapped to each member, three strategy docs designed for Claude, and a term sheet breaking down every piece of jargon. The VIP teams have already spun up their own meeting rooms off the back of it. Over 6 hours of member-led business sessions in the last two days alone. What you are getting in Premium is the prompt library distilled from all of that work. These are the Claude prompts that came out of those frameworks. Zero-spend audits, agency undercut pricing, content-to-client pipelines, the full set. Each one is ready to paste into Claude with your own business context. I want to be straight about why the tiers work the way they do. Turning live sessions into artifacts takes real time. I flew back from New York today and have been up all night building these out. My time is the bottleneck, not the courses. The courses scale. The artifact packages and live strategy work do not. The VIP tier is what funds that time so I can keep the free content flowing and keep Premium loaded with material like this. Premium members, Afternoon Tea is next weekend and you will be getting your own session package from that. More coming. For VIP members, full artifact package is in the Drawing Room course. Slide deck, three strategy docs, term sheet, the whole thing. Your Google form responses are coming tomorrow. 4/11/2026 - The Drawing Room (VIP) ·

Running Claude Code on Opus is powerful. But most turns in a session are mechanical, reading files, writing boilerplate, simple edits. You're paying top-tier rates for work that Haiku could handle in its sleep. Anthropic just released the Advisor Tool: A server-side pattern where a cheap executor model consults Opus mid-generation for strategic guidance. But it's API-only. Can't use it inside Claude Code. So I rebuilt the pattern inside Claude Code using what already exists. The setup: Opus stays in the orchestrator seat. It plans. It makes architecture decisions. It reviews output. It never touches files directly unless the task genuinely needs Opus-level judgment. Everything else gets dispatched to cheaper models: - Agent({ model: "haiku" }) — Claude subagents with full file access for simple edits - Agent({ model: "sonnet" }) — for multi-file changes that need moderate reasoning - A CLI tool (ask.py) that routes to Gemini, Kimi, MiniMax, or local Gemma via Ollama — for code generation, research, video analysis, anything where you just need text back The routing logic: Does the task need file access? → Agent tool (haiku/sonnet) Is the code complex? → sonnet or gemini Is the code simple? → haiku, kimi, or minimax (cheaper) Need video analysis? → gemini --video (native, no frame extraction) Need parallel research? → kimi-swarm (spawns up to 100 sub-agents) Want zero API cost? → gemma running locally via Ollama When a subagent hits something it can't handle, it reports back NEEDS_GUIDANCE. Opus thinks it through and re-dispatches with better context. That's the advisor pattern, strategic guidance exactly when needed, cheap execution everywhere else. Cost impact: A 10-task session where 8 tasks go to Haiku and 2 to Sonnet — your Opus tokens are only spent on planning and review. Maybe 20% of the total token volume. The other 80% runs at Haiku rates. With local models mixed in, it drops further. Open-sourced the whole thing:

We're restructuring how things work around here. Read this whole post!!! 🏆 WEEKLY COMPETITIONS START APRIL 20TH 🏆 Every single week, we're running a competition with cash prizes. Here's the catch: you have to be a Premium or VIP member to participate. The first one drops April 20th. We'll announce the challenge, you'll have a week to complete it, and the winner takes home cash. Every. Single. Week. If you've been thinking about upgrading, now you have a reason. Upgrade link: https://www.skool.com/quantum-quill-lyceum-1116/plans See you on April 20th. 🚀 📚 ALL CONTENT IS NOW UNLOCKED 📚 We used to gate Implementation Playbooks at Level 2 and Building Your Stack at Level 3. That's gone. When you join, you get everything. The Foundation. Implementation Playbooks. Building Your Stack. All of it. Immediately. Premium and VIP content stays exclusive to those tiers, but everything else is yours from day one. We're not going to force you to engage. This community works because people want to be here. 🎮 LEVELS NOW = REWARDS So what do levels mean now? They track your participation. The more you show up, help others, and share your progress, the higher you climb. And climbing comes with real rewards. How Points Work: - 👍 Like received: +1 XP - 💬 Comment: +1 XP - 🪄 Post that gets engagement: +3–5 XP - 🎓 Complete a lesson: +1 XP - ❤️ Helping others: bonus XP (manually awarded) Your title changes at each level. Everyone sees it next to your name across the community. 📐 Hit Level 8 — Free lifetime Premium membership. Already a paying VIP member? We'll upgrade you to free lifetime VIP. 👑 Hit Level 9 — 💰💰 $500 cash. Straight up. 💰💰 🏅 WEEKLY ENGAGEMENT LEADER = FREE LIFETIME MEMBERSHIP 🏅 Every Monday morning, we check the 7 day leaderboard. Whoever's on top gets free lifetime Premium membership. Already a paying VIP member? We'll upgrade you to free lifetime VIP. This resets every week. New week, new winner.