💪 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 to 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....

Everybody's a builder now. You open Claude Code or Cursor, noodle on a prompt for twenty minutes, and by Sunday night you've got a working app with auth, a database, and a Stripe checkout that actually processes a payment. I've done it. You've probably done it too. The first time it happens you feel like a wizard. And then the silence hits. You post it, you tell a few friends, maybe you drop it in a Discord... and nothing. Not "this sucks" nothing. Just nothing. No signups, no comments, no [censored] given, LOL. That silence is the lesson. And it's the same lesson that's existed since the first person built the first piece of software, it's just louder now because building got so cheap that everyone's tripping over it at the same time. Here's the thing nobody wants to hear: writing the code was always the easy part. Even before AI, a decent dev could smack out an MVP in a few weeks if they knew what they were doing. What separated the businesses that made money from the ones that didn't was never "can this thing technically function." It was always two other questions. Does anyone actually want this. And will anyone find out it exists. AI didn't change that equation. It just deleted the excuse. Ten years ago you could tell yourself "well, building takes so long, once I ship, people will obviously flock to it." Now you ship in a weekend and get to watch, in real time, that shipping was never the bottleneck. The market doesn't care how fast you built it. It cares whether it needed to exist. I think of it like the crepe analogy I keep going back to. Your first crepe is trash. Everyone's first crepe is trash. But with vibe coding, people are getting a hundred crepes an hour now instead of one a day, and they're shocked that crepe number ninety-four is still trash if the batter (the actual idea, the actual customer, the actual problem) was never right to begin with. You can iterate on execution speed all day. Speed doesn't fix a batter problem. So what's actually hard, if it's not the build?