If you are using an AI bot in your business, which calls people and interacts with them, be aware of THIS method that people may use to mess with, or even break your AI workflow. "Don't Hang Up On AI Scammers. Do THIS Instead." https://www.youtube.com/watch?v=lk3jCuITwcE I'm not sure HOW you protect against this kind of 'AI social engineering'. Given the way AI models are trained, Can You? I would never recommend people use this method themselves, against AI scammers and chatbots who robocall you continuously. I will say, I was rolling in my chair towards the end of the video though. Apologies if the moderators decide this is inappropriate and delete this post, but this group has the expertise to suggest actual fixes for ethical AI business users to prevent this, as well as the humor to appreciate the hack.

💪 It did not disappoint. 👉TL:DR - It made all AI use cheaper in my environment, made me more efficient, and it increased my memory system usage by almost half. It should be no secret to anyone here: I don't count tokens. 🪙 I'm on a Pro Max plan and I go where the work, and the passion takes me. But I have used Fable before, and I know about the token burn! So I came up with a plan! I pointed Fable at my own setup and pulled the report. 😅 I'm glad I did. Turns out it could've been cheaper and cleaner the whole time. I didn't ask Fable what it thinks. I pointed it at the real thing. My hooks, my handoff files, my subagent config, the actual token counts on disk. Two questions: where does the money go? & how do we spend less? 💡The answers. A silent forgotten tax on every message, A safety hook was injecting around 800 tokens into every prompt I sent. Repeated rules I already load once at the top. And a file that runs at every session start called itself " 450 tokens" in its own header. It was not... it was 7,000. My actual face when I saw this--->🤬 a few moments later--->😆 (Apparently, it's not only AI that is bad at counting sometimes!) My own file lied to me, and I'd read past that number a hundred times with a smile on my face! My long sessions. The ones I'm proudest of. Turns out that hour six is my most expensive and also least impactful at the same time. 💩 I know that models follow instructions worse at higher context. And because the quality was still there, the marathon I read as momentum was being billed to me at top rates for the weakest output of the day. 🙄 My helper agents were all running on the flagship (Most expensive model). These are the agents Claude spins up to send off to do tasks to get more accomplished in a shorter amount of time! This I knew about, and it was by choice, it's my environment and I never hit my 5 hour or weekly cap, so I did not care about this for myself, bigger = better right? Use Fable 5 on UltraCode in my environment, and we find out that logic was wrong....

There's a rule in teaching called backward design. You don't start with the lesson. You start with the assessment. Decide exactly how you'll know they learned it, then build backward to the activities that get them there. Sounds obvious. Almost nobody does it, because writing the test first is harder than diving straight into the fun part. Same trap with AI builds. We open a chat and start barking the build before we can say what "done" actually looks like. Then we act surprised when done keeps moving. The habit i borrowed from the classroom: if you can't write the check for "done," you're not ready to build. Not the feature, the check. One sentence you could prove true or false. "A new user gets from signup to first export without asking me a single question." Now every step has a target to aim at, and you'll know the moment you've hit it. Writing that sentence first feels like bureaucracy. It's the opposite. It's the thing that stops you building three polished versions of the wrong feature. And there's a bonus. If you can't write the sentence, you just found out the project isn't scoped yet. Better to learn that now, for free, than four hours in. What's your one-sentence "done" for the thing you're building right now?

What does everyone use to create markdown files with? I use LibreWolf as my text software and it doesn't. I know you can hand create in Notepad but I know there has to be a better option. I noticed that GPT seems to balk sometimes. I have it output the language for review, and then have it generate the md file. Last time I did, it mentioned that it doesn't exactly copy the review copy, just uses a summary of it. That didn't make much sense. Suggestions please.

Tiago Forte, well know for his work in AI memory, posted a YT video where he shows everyone, how he has his own personal folders set up on his computer. https://www.youtube.com/watch?v=A0pdL3MS_7E It's informative to see how the experts do it themselves, not just how they tell you to do it. I had to keep pausing it to look at the folders hierarchy, lol. (I looked but didn't see anyone had posted this.)