User
Write something
High Tea is happening in 6 days
Pinned
1983.
The past will tell you the future.
Pinned
Welcome to Clief Notes. Here's where to start.
1. Watch the intro video and introduce yourself in the intro post here 2. Start with The Foundation (free course). 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, move to Implementation Playbooks (Level 2). When you're ready to build your own tools, Building Your Stack (Level 3). 5. Post your work. Ask questions. Help others when you can. What are you here to build?
Poll
5905 members have voted
Pinned
Companies want to hire from Clief Notes. So we're building this.
Been sitting on this for a few weeks and figured it's time to show you. 👀 Over the last month, three companies have reached out asking the same thing. How do we hire people from Clief Notes. They've seen what folks here are building with ICM and they want that on their teams. Not LinkedIn AI experts. Not Coursera grads. People who can actually ship. So we're building it. 🛠️ talent.eduba.io Heads up, that's a demo. No real backend, no signups, no live data. Click around and you'll see what the full thing is going to be. A private platform where you list yourself with a real portfolio, companies browse, and they request an intro through us. We make the intro. You take it from there. Few things worth knowing. 🔍 Every profile gets reviewed by the Eduba team before it goes live. The quality bar is the whole point. 🔒 Companies don't see your last name, your employer, or your contact info until we make a formal intro. You can block your current employer too, plus five more companies if you want. Nobody you don't want seeing you sees you. You can list as actively looking, open to offers, or not looking. Passive welcome. Honestly most of the strongest people we've trained are employed and plan to stay that way until the right thing shows up. That's fine. Sit on the platform, see what comes through. 💰 When a placement happens you get a $500 to $1,000 bonus after 90 days in the role. On top of whatever you negotiate. We pay you for staying. This is why the community matters. Companies aren't asking us for resumes. They're asking us for the people who already get it. ICM, agent architecture, knowing when not to use AI. That's not on a LinkedIn profile. Go click around. Tell me what's missing, what's confusing, what you want to see when the real thing ships. We're already building it. 🚀
🏁 Foundations 4.5 Check-In
You just saw how context changes per task. Vote below, then tell us in the comments: what two areas of your work did you set up, and did Claude behave differently in each one?
Poll
187 members have voted
🧪 New benchmark out
New benchmark out of Meta FAIR, Stanford, and Harvard called ProgramBench. The setup: you get a compiled executable plus its docs. Source code stripped. Rebuild the program from scratch in any language you want. Tests check input/output behavior against the original binary. 200 tasks, from small CLI tools up to FFmpeg, SQLite, and the PHP interpreter. 📊 Results across 9 models: Zero tasks fully solved. Opus 4.7 was the best, passing 95% of tests on only 3% of tasks. GPT 5.4, Gemini 3.1 Pro, and Haiku 4.5 hit 0% in that bucket. The interesting part is section 5. Even the model solutions that "worked" looked nothing like the human reference. Median 1,173 lines vs 3,068 in the original. Flat directories. Fewer functions, each one longer. GPT 5.4 wrote 96% of its final code in a single turn on most tasks and never modified existing files on roughly 40% of runs. 🎯 Why it matters for us: The benchmark separates writing code from designing software. Models can produce syntax all day. They cannot yet decompose a real system into coherent modules, pick the right abstractions, or organize a codebase the way a working engineer would. That gap is what computational orchestration points at. It is also where the durable value lives. 🛠 Try it: Pick an easier task from the repo (the paper flags nnn, fzf, gron, and jq as more tractable). Run it against Claude or your model of choice. Watch where you and the model split. Note the design decisions you make that the model never even raises. Post your runs and attempts to create a harness that would allow the model to do it. Wins, failures, weird outputs, all of it. 📍 Paper and Repo: ProgramBench I'm building something on top of this right now. More soon.
1-30 of 1,324
Clief Notes
skool.com/cliefnotes
Jake Van Clief, giving you the Cliff notes on the new AI age.
Leaderboard (30-day)
Powered by