I’ve been playing pokemon go so much recently. I’ve made a lot of progress in the game, but I really worry that I’m getting addicted because of how stressed out I am right now.
I stressed out about my relationship and about my career path moving forward. I want to make sure that work does not take over my life and that it stays aligned to what I want to do moving forward.
Every time I feel stressed, I reach for the pokemon go. Holy shit, I am addicted.
I feel very tired, but no longer sick. That is a good thing at least.
I’m going to walk around the airport. And this time, instead of catching pokemon, I am going to meditate and think.
On the plane I meditated on some of my issues and I came to a big realization. The first step to feeling or processing any pain is to notice and name the pain that exists. I spend so much time avoiding thinking about painful emotions or experiences, avoiding thinking about how things hurt me it makes it hard to face the pain at all since I’m not taking the first step,
I want to focus on doing that more now as the first step to processing more emotions.
I just came back from standup paddleboarding and I feel really really good. Everything is clear and easy to see. I need to find a way to go and play on the water more.
I also was thinking about how if the eye is constantly in a state of contraction, we might need to do some sort of massage in order to help loosen and relax the ligaments and the muscles. I don’t know yet what kind of massage will work. All the current massages only target the areas around the eyes.
I wasn’t able to test my vision on my phone because it is out of battery but I tested on very small text on a book an the results are mindblowing.
So I’ve been thinking a lot about, well sales. This video sums it up pretty well.
I have been focusing on a lot of things recently, coaching, youtube, France and my girlfriend and on top of all of that, work and my day job in AI consulting. I recently decided to say fuck it for everything but three things:
My girlfriend and relationship – we don’t have much time together and I want to enjoy it
Exploring France – again not much time, amazing opportunity to relax and explore
Going crazy as an AI Consultant and bringing in a crazy amount of business
My relationship is going pretty good, and for France I don’t want to think about it, I just do whatever I want. So let’s focus on the last thing.
I want to do exactly what Mark Cuban said. I want to be the best-performing salesman at my job. I want to take that experience to build my coaching business. I want to use my success to do consulting like I do coaching and have a lot of fun. I want to use my success to request more pay.
I want to learn how to master content creation. Build a social media presence. Build my connections. Get the reputation and respect that I’ve always felt I deserved.
The main conundrum I’ve been facing is this:
How much information do I give away?
If I give away tons of free information, what are they hiring me for?
If I give away free 30 minute sessions, does that mean I will never talk to them ever again?
After some meditation, I came up with the following thoughts:
I can give away everything
For focusing on their specific problem. The most difficult thing is not to come up with a solution it is to come up with a solution to the right problem (just like coaching)
No, I can always talk to them again. In fact, I can give away unlimited 30-minute sessions. However, it isn’t about the 30 minutes in the session that costs me a lot. It is the 30 minutes of research that I need to do before the call. It is the structure of writing out a plan for them that is costing me more.
I can always have more conversations with less prep or even more 30 minute conversations with them.
In the future, if they pay for consulting, they are paying me to invest more deeply into their solution. That means more research outside of the calls. That means more knowledge of their product and aligning my goals with theirs (just like in coaching).
If I wanted to sell educational products, the cost for me and the added value for them would be in the way I packaged the information. Not the information itself. For example, a special website, platform, a book or an app.
There are three parts of a solving a problem:
Having the knowledge
Transferring it to someone
Using the knowledge to solve the problem
When you create free content, you are mostly some #1 and some #2. I use a lot of my current knowledge + a little research + some production (design, videography, writing).
When I get on random calls with people, it is a little #1 and a little #2. I’m using my current knowledge with no research, and trying my best to transfer it to someone on a call.
When I get on “free” high value calls with people, I’m doing some of #1 and some #2 and a tiny bit of #3. I do a lot of research, use my current knowledge, trying my best to transfer the knowledge, and might even implement a small deliverable (like a roadmap, plan, strategy, or diagnosis).
When I’m doing consulting for them, I’m doing a lot of #1 and a lot of #3 with some #2. I’m doing tons of research, using my own knowledge, leading the charge on actually solving the problem (either building it myself, finding the right solution to buy, or hiring the people needed to build it), and doing a bit of education.
When I’m selling an education solution, I am doing a lot of #1 and a lot of #2. I’m doing tons of research, and spending a lot of effort on transferring the knowledge.
Yesterday I was vlogging a guy \asked me if I was a YouTuber, and he asked me all these questions like what my channel was about and how many subscribers I had.
I felt REALLY self-conscious because I AM a YouTuber, but not a famous or successful one and I feel like I’m disappointing people when I tell them that I have three hundred subs. I realized a few things when I felt the feelings of shame:
People LOVE the idea of youtube, you don’t need to be big for people to be excited about it. Sure some people will judge you but I think most people like the idea that you are trying to succeed and are probably curious enough to look me up and subscribe. In fact, isn’t that what I want? People who are legitimately interested in my journey subscribing to me?
I’m always REALLY self-conscious when people stare at me when I’m vlogging and I always try to solve the problem by either NOT vlogging or trying to ignore the embarrassment. I realized that there is a third better option. Any time I’m feeling embarrassed, I should just feel the feelings until the right path becomes clear to me. Usually, I feel so uncomfortable I will do ANYTHING to avoid the feeling, but I should just embrace it as I should do in any uncomfortable situation.
A couple of weeks ago, I rented a car at National car rental. My sister returned it for me, and I got a shock in my email a few weeks later.
I immediate assumed this had to be a scam, or some sort of mistake. But the more I read, the more that I could tell this was actually legit. They had the right time, the right place and right company. They were charging me for $1295.81 for damages to the vehicle.
Looking at this deeper I noticed that the line items were VERY extensive, replaces door parts and handles. According to them, the car was HEAVILY damaged.
Looking at the pictures, I could barely see any of the damages they were indicating. It almost felt like they were offloading the cost of wear and tear on me.
Obviously I was LIVID.
I knew that there were some small marks on the car when I picked it up, but I never took any pictures.
I knew that no damage whatsoever happened when I had the car. I didn’t think any of this damage was on the car when I picked it up, but the damage in the photos are so subtle its hard for me to be sure.
I had rental insurance specifically for this car, but didn’t want to file a claim for something I didn’t do.
My sister had someone walk around the car and CONFIRM it was ok before she returned it. They parked it, and who knows what happened after that.
National has a service for their “Emerald Isle” premium members where you can pick up and drop off a car without ever seeing someone.
This now seemed like a LIABILITY not a PERK since now I can’t get them to acknowledge damage on the car.
I’m a new member and if they were going to be f*cking sticklers about this whole thing, they should have EXPLAINED it to me. I would have got them to sign off on EVERY F*CKING SCRATCH BEFORE AND AFTER returning the car.
So I went to chase down this problem:
I called National Support, and they told me that I needed to call their damage unit. I asked them to make a note on my case so I wouldn’t have to repeat myself.
After I called their damage unit, they redirected me to someone else.
After getting to another person, they redirected me to someone else.
The last person seemed to know what they were talking about, but I had repeat myself because she could not access any of the notes that National Support wrote down.
The last woman who oversaw the appeals to the damages told me the following information:
Generally its better if you take photos beforehand, however, in situations where the “damage” is so small it is easy to miss, you can appeal and they will dismiss it. They consider it human error.
She told me that my “damages” were definitely small enough that someone might have missed it before (so it may not be caused by me).
She agreed to waive all of the fees.
So my lessons learned from this whole experience:
Always get rental car insurance just in case.
Take a video when you pick up the car to prove the condition of the car beforehand. (It’s gonna be me in the parking lot being like “hey this is me in the parking lot picking up this car at X time” so they have proof I didn’t take the video at some other place or time)
Take a video of the car when you return it.
If they try to charge you for something really small and not visible in your videos, appeal, and they will probably dismiss it.
It’s good to be a mix of legitimately angry (I was furious) but polite at the same time (I apologized in advance telling them I was very upset but I knew it wasn’t their fault personally). As a result, they were helpful and resolved my issue quickly.
I was in Taichi class the other day and my instructor said something very interesting.
She told us that if you are leaning forward, then you are “giving too much”. And if you lean back too much, you are “accepting too much” and when someone gives you a compliment, all you need to do is say a simple thank you.
It is an very interesting concept in taichi, this idea of always being in balance, always sitting on your heels even when pushing forwards.
I really want to experiment and see how much I can apply this to things like Valorant or productivity.
It was really easy to write in my notebook about my AI game.
Perhaps it will get harder when I actually try to code it.
I came up with the basic architectures.
Super Basic MVP Stack
Streamlit
Python vector db
Free MySQL
Production Stack
WordPress + NodeJS
AWS
VectorDB
MySQL
I also came up with a bunch of mini challenges that will help me get to the Basic MVP done.
Goals for the MVP are:
Determine the overall AI technologies needed
Come up with estimated overhead to run the game
Raise money/interest
Mini Challenges for MVP:
Create and pull from vector databases in python
Work on data structures:
Story summary
Last 3 transactions
Story summary
Main objective
Geography
Locations
Lore
Physical properties
Characters
Stats
Age
Race
Health
Strength: A character’s physical strength, such as how much they can lift or punch
Dexterity: A character’s precision, agility, and nimbleness
Constitution: A character’s physical fortitude, such as how well they resist damage and disease
Intelligence: A character’s raw IQ and ability to learn
Wisdom: A character’s spellcasting ability
Charisma: A character’s spellcasting ability and saving throws
Location
Updates
Backstory
NPCs
Stats
Location
Backstory
Motivation
Relationship matrix
Time
Visibility mechanism (to see who gets to see and interact with a new transaction)
Overall prompt
Story summary mechanism
Query past with locations and time
Develop multi session chat in streamlit
Teach LLM examples
Battle
Non standard battle
Player enjoyment
Plot armor
Changing objective
Map movement mechanics
Later development challenges:
Explore invalid response resistance (create a way to repair responses)
Explore cost-cutting and LLM selection
Explore personality extraction (of NPC’s or characters)
Explore context length restriction problem solving
Writing all this down I’ve come up with two steps moving forward:
Even simpler MVP – completely prompt based
After getting interest, develop simple MVP into NodeJS + frontend
Then work on full final product
Tool calls might be a gamechanger as well as vector databases
I’ve done it. I hit the wall of sinking dread, exhaustion, and boredom in this project.
I don’t want to create a DND game focused on storytelling with AI. AI just isn’t good enough, masterful enough, creative enough to create a rich world.
I want to focus on creating a game similar to the games I always wanted to create, focused on strategy and cool mechanics based in a system that allows for infinite creativity.
I need to create a system that builds a reality, not tells a story, and lets the player interface with it in a seamless way.
That means I’m adding a challenge:
Think about how to allow for the user to have multiple inputs
Speech – what your character says
Action – what your character attempts to do
Question – what you want to ask the DM
Separate the types of responses
Speech and actions get translated into story
Questions are responded to
Think of how to use fewer words and show more
Character sheet
Map
Voice input and output
Also, I take back what I said, I can make a game on LLMs that tells a story, even though the thought of it makes me queasy in my chest for some reason.
I have then the challenges related to storywriting:
