💪 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....

Looking for people's opinions on something - please speak up. I am blessed to have a handful of high-end professionals that I can discuss AI with. I suppose I use them to help me sharpen my growing spiel for AI, and they likely trust that they are learning something along the way. There is a part where I want to guide them into a place where it is obvious to them that sometimes an LLM alone cannot provide a full level of expertise, and people will have to augment the LLM. Here is the example I use. I say, quite honestly, that I would 100% trust an AI to give me a few home exercises for my two 10lb weights, as an ankle sprain is keeping me from running. I trust any LLM to summarize that for me from the LLM's transformer training. Then I say that I think it is obvious that a third year NBA player would be crazy to ask an LLM, 'I am a third year NBA player going into the final year of my rookie contract. Please give me a summer workout plan before training camp starts in the fall.' - well, maybe not crazy to ask, but crazy to follow that advice without any other input from trainers, his NBA team, etc. It is supposed to be a fun example that guides the conversation into what do you or your company do that is unique and to begin the discussion about methods to add their expertise into their operations. And it worked a few times, until tonight. A high end real estate executive asked me, 'don't you trust an AI to summarize a workout plan for an NBA player?' I thought the answer was an obvious no... but perhaps, live and learn?? I guess I am asking for advice on two things. (1) Do people trust an AI to give an NBA player a workout plan. And (2) How do I fix my example/spiel. I don't want to talk about NBA athletes. My desire is to get people to talk about what they do that is unique and how AI (okay, ICM) can help them. I don't mind a bit of failure, but failing twice in one sentence has lead me here to ask for advice.