I made this so I can run commands in the terminal with less copy and pasting https://github.com/zazencodes/aicmd I'm looking for early users to test it out. Please help me out guys! 1. give the repo a star on GitHub ⭐ (thank youuuuuu) 2. install it and try it out curl -fsSL https://github.com/zazencodes/aicmd/raw/refs/heads/main/install.sh | sh I built this for myself and it works great on my system but I need your feedback It works with ollama, llama.cpp, APIs (openai, claude, gemini) and CLIs (codex, claude code, antigravity)

I feel like there’s so much waste right now when I’m using something like openclaw to do a very simple specific task. For example I’ll get it to “add a quote “ to my quote collection in Obsidian Or to “add an expense” to my bookkeeping system These should be specialized workflow-oriented agents. I think I could easily spin up an app with a pi backend system to do this. Might make it into a course. What do you think? Would you be interested? Also let me know if you have (a) advice or (b) questions

1) share what you’re building right now AND 2) post a photo of your workspace setup PS. If you’re working on multiple things then please share the one that’s most fun ;)

1️⃣ My weekly skool calls are free for everyone to join (30min demo + 30 min Q&A) 2️⃣ The call is recorded each week and uploaded to the Classroom (for premium members) 3️⃣ My "Programming Book Video Guides" are free for everyone BUT you have to be level 2 You level up on skool by getting 5 “likes” on your posts. Just follow the steps below: 📸 POST A PHOTO of your workspace in "What are you working on?" https://www.skool.com/zazencodes-agentic-coding-club-7823/what-are-you-working-on 👉 CREATE a post about something that's on your mind 🤝 REPLY to a recent post to add value 👍 LIKE other people’s posts (you only level up by getting likes) 2) check the "Calendar" and add my next call to your personal calendar - Look at the topic of the call (the build — first 30 minutes) - Jot down any questions that you have for me (the Q&A — last 30 minutes) 3) start on your learning path - PAID members go to the "Classroom" and complete the "Introduction" first - FREE members check out the course previews on my website: https://zazencodes.com/courses 4) add a new post in the "Community" when you've completed a course! - I'll send you a course completion certificate that you can share on LinkedIn 🎓

There is this idea of self-learning in AI. Am I smarter today than I was yesterday by learning from yesterday's mistakes? Does anyone have any practical suggestions on this self-learning? I am seeing this tension. If the instruction is non-deterministic, then there are issues like prompt hacking. Besides the vulnerability aspect, there have also been numerous cases of AI agents not doing specifically what was asked. This "may or may not happen" aspect to any plain English instruction given to an AI agent. It's a request not a command. The way to solve this is to convert the instruction from plain English to some coding language and run that piece of code. Usually python works. But moving to python kills the self-improvement loop. All self-improvement options I have seen (SkillOpt for example) work on improving instructions in plain English. A request can improve over time but a command is frozen in the time it was created. Wonder how people see this tension of being more efficient today (python code) vs being smarter tomorrow (Prose in a skill)?