| | | |

Learning Time: Young Founders and Opensource AI Ideas

Byjack

I’ve been feeling extremely behind in AI and entrepreneurship and I’ve been feeling a desire to catch up.

But at the same time, I don’t want to get too overwhelmed and manic about my learning process and want to take it one step at a time.

Here is a catchup on the latest videos I’ve watched:

Similar Posts

The Perfect Job

Byjack

For the longest time, I’ve thought that my job was pretty much perfect. It wasn’t the highest paying job, or the one that I loved the most, but I think it has many many good elements such as:

  • Good enough pay to never have to worry about money
  • Good work/life balance, lots of work sometimes, little work others
  • Lots of traveling
  • Get to practice speaking and work on fun projects

Obviously, I could find a job even better in every area, but this is quite good already.

I realized recently why I still feel tired and think that it is too much work so often. THE WORK LIFE BALANCE IS HORRIBLE.

Ok, I understand I just contradicted myself there, but the reason why I think the work life balance is good is because on paper, there are lots of downtime where I can do whatever I want. However, because of the amount of emotional pressure that I put on myself, I’m actually always thinking about work which means that there is actually no worklife balance at all.

I worry if I kick back and ignore work for a while:

  • I will not be able to focus when I really need to so I need to get all the work done that I can
  • I will not be able to have enough time to get my work done when I really need to so I need to be working all the time
  • Someone will ask me what I’ve been working on and I will be outed as someone who is not contributing anything

Some of the anxieties I have around actually working:

  • I worry I will create ugly applications and I will come off as bad and incompetent
  • I worry I will not build enough for my application and I will come off as lazy or incompetent
  • I worry that when I go into meetings I will look unprepared and stupid

If I am able to deal with the emotional burden of this job and turn work into something soothing and relaxing for me, I will actually be so happy in this job. This will be the easiest money I will ever make and it will free me up to make money in other ways as well.

I’m going to do this in a couple of ways:

  1. Practice acceptance of where I am. Give myself permission to be bad
  2. Reprogram the idea that I will be rejected if I am not perfect
  3. Look for ways to make my job extremely easy
  4. Find ways to meet my needs through my jobs

So Step 1:

I am lazy, incompetent, unproductive and stupid. I accept myself for it. I give myself permission to be this way as much as I want to be.

Step 2:

The Bossy Man

In the meeting

Which I spent

Almost no time preparing for

He asked me to show

Something

I didn’t want to show

I said no

The meeting

Was under my

Control

 

The Finicky Architect

I created something

That I didn’t think

Was good enough

To stop him from asking question

Yet I showed up not to impress

But to help

And we were both happy

By the end

Step 3:

Where are the hardest parts of my job?

1 – Learning about new technology

  • Takes a long time
  • Hard to know what to focus on
  • Hard to remember

Ideas on how to make it easier:

  • Create materials for myself to make my life easier (cheat sheets, presentations)
  • Look for a way to make my life easier
  • Timebox an attempt to learn quickly
  • Focus on one area that has impact

2 – Building mockups

  • Takes time to understand the customer’s process
  • Hard to formulate what I need
  • Hard to understand how to design it
  • Hard to work out the technical parts of building out a process

Ideas on how to make it easier:

  • Clearly articulate what I need
    • The interfaces
      • What the style is
    • The processes
    • The data structures
    • The priority
  • Get help on the UI
  • Get help on the build itself

3 – Presenting the product

  • Never know what they will ask me to explain or click on
  • Hard to boil down the flow to a few steps
  • People may want to test you on areas that they don’t understand or may be hard to show

Ideas on how to make it easier:

  • Get the clarity I need:
    • Why they are asking the question?
    • What are they testing me on? What is the thing I need to prove?
    • What do they already know or understand?
  • Pause
    • Think about my gameplan
    • Use metaphors to bridge understanding gaps
    • Walk through what I’m about to do in my head before I do it on the screen

Step 4:

The most annoying things at work and how I will meet my needs through it:

  • Building mockups
    • Contribution: Who am I helping with this?
    • Growth: What will I do better with this demo?
    • Significance: What special signature will be mine?
    • Uncertainty: What is it that interests me the most about this demo?
    • Certainty: What do I want to copy? Who can make my life easier? How long do I need realistically?
  • Filing expense reports, doing training and filing quarterly reviews
    • Love and Connection: Who can I have a working/hangout session with?
    • Uncertainty: What time challenge should I give myself?
  • Boring meetings/trainings
    • Certainty: Why am I joining? What questions do I need to ask? If none, make a note of what I need from the meeting and watch the recording.
    • Love and Connection: Reach out to the presenter and tell them what you liked
  • Giving demos and presentations
    • Contribution: How can I be the most helpful?
    • Significance: Why am I showing this? 
    • Uncertainty: Don’t prepare
    • Certainty: What am I afraid of?

Ok, that’s it for now. I will say that writing this blog post has been tremendously helpful. I will be referencing this over and over again it is just so useful. Hopefully after using it many many times, it will be ingrained within me and I won’t need to look at it anymore.

| | |

UNIT TWO: Processing pain + work (day 3)

Byjack

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:

  1. Determine the overall AI technologies needed
  2. Come up with estimated overhead to run the game
  3. Raise money/interest

Mini Challenges for MVP:

  1. Create and pull from vector databases in python
  2. 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
  3. Visibility mechanism (to see who gets to see and interact with a new transaction)
  4. Overall prompt
  5. Story summary mechanism
  6. Query past with locations and time
  7. Develop multi session chat in streamlit
  8. Teach LLM examples
    • Battle
    • Non standard battle
    • Player enjoyment
    • Plot armor
    • Changing objective
  9. Map movement mechanics

Later development challenges:

  1. Explore invalid response resistance (create a way to repair responses)
  2. Explore cost-cutting and LLM selection
  3. Explore personality extraction (of NPC’s or characters)
  4. Explore context length restriction problem solving

Writing all this down I’ve come up with two steps moving forward:

  1. Even simpler MVP – completely prompt based
  2. After getting interest, develop simple MVP into NodeJS + frontend
  3. Then work on full final product
  4. 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:

  1. 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
  2. Separate the types of responses
    • Speech and actions get translated into story
    • Questions are responded to
  3. 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:

  1. Franklin’s elements of a story
  2. Dialog
  3. Emotion
  4. Character development and growth
| | |

Profit in Peace 2: First Day

Byjack

Today is not the first day working on the Profit in Peace challenge, but it does FEEL like the first day I am living it.

Today is the first day when I dedicated my morning to finding my magical life. For some context of what that means:

Something that I still don’t really understand or feel comfortable with applying is the values that I believe in every day.

I think that writing honestly and focusing on myself in this blog every morning might actually hit all of these points:

  1. Honesty – well, this blog isn’t called unfiltered for no reason! I do remind myself all the time of the “if they don’t like me please leave” mentality.
  2. Imagination – for me, this blog is dedicated to all my imaginative parts: art, YouTube, philosophy, poetry etc.
  3. Intuition – this is the place where doing things “my” way is celebrated and I tap into what is the best way to do something (according to my intuition) rather than how everyone else does it.
  4. Empathy – this blog is a lot for my feelings where I process feelings through words, video, and images. It is a part of honesty too, honest emotion where this is my place to express everything imperfect.

I also like using the blog as my way of living out all my values and being the person I want to be because it really feels like I am sacrificing something to do this…in a good way.

JT Franco talks about if you aren’t willing to sacrifice for what you want, what you want becomes the sacrifice. In the end, I had no idea whether I would sacrifice time talking to my girlfriend, going on YouTube, working, playing games, or making YouTube videos. Those are the things I spend most of my day doing anyway. But none of those things seemed right. It was too blunt on an idea, how could you sacrifice all of YouTube? How could I sacrifice all of work?

But by sacrificing my mornings, in a way, I am also sacrificing all of those things. I resist the urge to listen to audiobooks, watch YouTube videos, check messages, or work in the morning. I dedicate all my time to working on my blog and all my challenges, thoughts, ideas, and philosophies.

I also feel a deep unease and anxiety keeping pace with me this morning:

I’m Afraid I My Boss Will Check

I’m afraid my boss will check

See I’m not working

It won’t matter that I have bigger dreams

it won’t matter if I did a bunch of planning

On the weekend

Feverishly, desperately trying to

Make my workday

Productive, efficient enough

To make up

To make it easy

For me to balance

I remember the look on his face

When I told him

I like to meditate

Skeptical

And

I also wonder

If finding my magic

Will make me feel sad and lonely

Like I did yesterday

I feel tired as I

Let go of trying to change the feeling

And accept it instead

Another anxiety that I have about this challenge or this “morning commitment” is just the sense of lack of clarity. I don’t know what I should be working on, or what I can work on. I think is the pressure of time. Or maybe its because I completed all the prework for the challenge and I don’t exactly have something to work on right now. I’m afraid every action is not “right”.

Is it the right thing to:

  1. Work on challenge videos?
  2. Work on editing videos?
  3. Work on reaching out?
  4. To focus on my body?

Wow there is so much here and I feel that I may be stalling. Scared to make a decision so I’m just rambling on a super long blog post that doesn’t really say anything in particular.

Well all I know right now is I feel like doing a bit of freewriting, fantasy writing or something of that nature. So I’ll go do that.

| |

Profit in Peace 15: Workplace Reflections

Byjack

I had quite a stressful workday as I expected but I wanted to jot down a couple of reflections today:

  1. Reminding myself of my boundaries (time, respect, honesty, empathy, and possibility) really helped
  2. It also helped to note down what I cannot control before every major meeting (usually something related to how someone felt about me)
  3. I noticed that keeping pace with my todo list was helpful:
    1. Keep all tasks that come to mind in my todo list (use it as a mental trashcan to throw all my worries)
    2. Reorder todo list to whatever I am working on right now (move something to the top if I am currently working on it)
    3. Do tasks immediately if they are low-effort
    4. Do sweeps (try to do everything on the todo list)
  4. Focus also helped
    1. Close as many tabs as possible
    2. Focus on one thing at a time

I was thinking about how to transition from work to Valorant more effectively since I usually start to feel dead and I end up watching youtube and ordering food and that kind of makes it hard for me to stay sharp when gaming and I end up feeling even more stressed and awful.

I think cleaning is a really good transition point. Cleaning reduces stress and is a great way to transition slowly…if I’m worried that there will still be a call coming in and I might have to go back to work, cleaning makes it easy to go back to work without feeling like I am not ready to transition to the next thing. In fact, if I clean, even if I go back to work, I will still be more ready to game after the work is done because my space is now clean.

I also like the idea of a mental dump to write down everything you are thinking about at the end of the day so that you can pick it up at any point today or tomorrow or the day after.

Finally, I like to look at the schedule for the next day and mentally prepare for it to know what you can do today to give you a lot of spaciousness tomorrow.