User
Write something
Afternoon Tea is happening in 8 hours
Pinned
Welcome to Clief Notes. Here's where to start.
1. Go check out 📚Navigating The Course to see how to get around and what's here. 2. Start with The Foundation. Concepts, folder architecture, prompting framework. Everything else builds on this. 3. Check in at the bottom of each lesson. Polls, discussion posts, other members working through the same stuff. Use them. 4. When you're ready to build real things join in on our Biweekly competitions and win some real cash. ⭐ Competitions Mega Thread 5. If you are wanting to dive into the masterminds, grab all the past templates, artifacts and resources. Upgrade and head into the The Vault for Premium and The Drawing Room (VIP) for VIP 6. Post your work. Ask questions. Help others when you can. What are you here to build?
Pinned
🚨 New one in the NLP Logix series is live 🚨
Sat down with Katie Bakewell, a data scientist who's been building this since 2011, back when it was still just called "natural language processing" 🧮 She came up through math (DNA computing, time series on commodities) and thinks about problems like proofs, not recipes. What we get into: 🪨 The Indiana Jones "build me a chatbot" boulder she ran from in 2023 🚨 The 7 neural nets that "found" a signal that was completely fake 🏎️ A $5M Pagani vs a $100 Toyota, and why "best" is a trap 🤖 The first chatbot was built in 1966 (ELIZA)... these aren't new ideas 🐬 Meta's SAM3 turning hours of labeling dolphin fins into a single prompt 🧠 Why half the companies asking for AI are solving the wrong problem ▶️ Go watch 💬 Then drop a comment: What surprised you most, or what would you have asked her? Happy learning 🙌
Pinned
🤝 NEW: The Connection Hub is live
👋 Welcome to the Connection Hub - The Vault · Clief Notes So I was on the onboarding call this today, and one thing kept coming up that I couldn't stop thinking about: The biggest value of this new age isn't just the tools. It's the people. 👥 Specifically — people who understand AI the way THIS community teaches it. Not "prompt hacks" and not "10x your output" nonsense, but actually building systems, thinking in workflows, and treating AI like a real part of how you work. That's a rare group. And a lot of you told me the same thing: 💬 "I'd love to work with someone who gets this." 💬 "I want to break into [industry] but don't know anyone in it." 💬 "Who else here does what I do?" So instead of letting those connections happen by accident... I built a place for them. 👇 🗂️👋 Welcome to the Connection Hub - The Vault · Clief Notes It's a simple set of pages, split by industry. You find your corner, drop a quick intro about what you actually do and what you're looking for, and connect with people who speak your language.
Connection Hub: 💼 Business & Finance
Intros for The Connection Hub - The Vault 👤 Who I am: (name + where you're based) 🛠️ What I actually do: (the specific work — not "I'm in real estate" but "I run a 3-agent team doing residential resale in Austin") 🤖 What I'm building with AI right now: (your current project, workflow, or the thing you're stuck on) 🎯 What I'm looking for connection-wise: (pick one or two) 💡 Someone who's solved [X] 🤝 A collaborator / accountability partner 👀 Just here to learn from people in my field 🧰 Trading workflows & systems 📬 Best way to reach me: (DM here / comment / link)
How do you stop an agent slipping into the wrong project when two of them look alike?
This isn't prompt drift — it's identity drift, one level up, and it's been actively costing me. Some of my projects were spun up from the same template, so their Layer 0 is byte-for-byte identical to a sibling's. A couple are forks — a derived project that kept the original's identity wholesale. When I open one of those folders, Layer 0 loads, the text is indistinguishable from its twin, and the agent gets zero distinctive signal about which project it's actually in. Priors and memory rush in to fill the vacuum, and it quietly starts working the look-alike instead. The annoying part: each project has the right identity written down — a manifest with the correct name. But the manifest isn't read at startup, so it's the "written ≠ loaded" problem again, just at the level of project identity instead of a single fact. Correct on disk, absent from context at the exact moment it matters. What I'm weighing, and where I'd love other eyes: A negative-definition line at the top of each identity file — "this is NOT [the twin]; derived from it on [date]; changes here don't propagate upstream." The Gloss "not-this" move applied to identity. A fail-closed startup hook that stamps the session with the project id + a "don't confuse with" list, and warns when there's no manifest. Deterministic, not doctrinal. A clone check in the drift script: two projects with an identical Layer 0 = fail, caught before it ships. My working belief is that written instruction won't fix this — I've proven that to myself — it has to be enforced at runtime. So: if you run a lot of similar projects, how do you keep the agent from slipping into the wrong one? Do you enforce identity deterministically (a startup hook/stamp), or is there a lighter structural trick I'm missing? And has anyone found a clean signal for "this folder's identity is load-bearing at startup" rather than just present in the tree?
1-30 of 2,428
Clief Notes
skool.com/cliefnotes
What we give away free beats most paid courses. Build durable AI systems with a Marine vet and Edinburgh researcher. 40+ lessons, growing.
Leaderboard (30-day)
Powered by