
??? stay tuned... π οΈ Former Creative Tools Designer for @FNCreate @EpicGames
Eugene, OR
Joined April 2010
- Tweets44.7K
- Following1K
- Followers3.5K
- Likes131K
πππ Week 2 of Claude Code
It's been a wild week, and my AI sentiment is growing. It's a powerful, but dangerous tool. But like a knife can be used for bad or good. Gen AI IS bad, mainly because it allows bad capitalistic actors that don't care about other humans to keep them out of the process rather than making space for them to thrive.
However in the hands of the right people, it is absolutely an accelerant. I'm an automation engineer with HIGH standards for good automation. So finding the right way to train AI and the right things to add/remove from the workflow is crucial to being good at it.
Quickly realizing that several harnesses/success gates aren't as necessary as I thought. So if you aren't cleaning up things regularly and rethinking your workflow, you are wasting valuable time/tokens. Your ROI on AI starts to drop. I did hit max usage on my $100 plan for Fable, and 84% for all other models.
My primary goal was teaching it everything I've been doing for the last 3 years. I needed it to understand the timeline and the goals. Both for our own record and also for its own understanding of WHY the code is very different.
Took me about 3 days to fully go through with it. And after that the rest was really, how do I get it introduced to what we are doing on a small scale. So since the end of the first week was creating a good art pipeline that supports human artists, I decided to have that art pipeline output interact with the framework. And this morning was the final test of something with basic art functionally fully working landed and meeting the standards of the framework enough to work with it.
Now every widget's art comes from that art pipeline, and the `Close` button at the bottom of the screen was also created as its own component for the framework and works exactly as I need it to. Close the UI. Well act as an action button really.
So this was the first slice of getting AI into our own company's work. And I feel really good about what's about to start happening with our own product. The basic art styles of all the widgets now come from our art pipeline, the widget scaffolds to work with the framework are now built via AI. And that close button is all of it working together for new functionality.
This next week is getting my second brain online and then teaching AI to do a larger part of the framework to add more substantial features. I'm stoked for the future ahead.
πππ Sad face... this is TOO much like @BroccoliGames Coffee Caravan. Like use the power of AI to be creative at least.
You have the power of a genie at your fingertips folks. Use that extra time you gain to do research and experiment. It's a beautiful time to be an indie.
Sadly not everyone has the privilege to make that sacrifice. Ultimately, I had to make the choice to switch because it's been so hard getting a job otherwise. This space is filled with so many who disagree with my own opinion, experience, and passion that I can't get a job and can't feed my family.
So I hope you understand that while you are able to make that moral choice, not all of us can. Some people can vote with their wallet, but that's only the people who actually have the privilege of having a wallet right now.
The real problem with AI really is the capitalistic side of it. That it robs people of their survivability. I have near 25 years of engineering experience. I always felt like I could fall back on that if things didn't work out in game dev. In the past year that relevance of that ability disappeared so fast.
I respect those of you who can afford to be anti-AI, but I hope you don't judge those of us who have had to make the choice to switch for survival sake. Because it was designed to basically force us into this situation at some point.
And I can't get a normal job any more. When you've been paid at a certain level, every normal job just worries that eventually you'll leave so they go with someone else. Being "over qualified" has been a real problem for my survivability.
And there's too many people in this space with too high an ego that have barred me from getting work behind the scenes. So to the few people that have given me opportunities, I appreciate you more than you know. πππ
π₯Ίπ₯Ίπ₯Ί Day 2 of Claude Code
Alright I'm 48 hours in y'all, and 2nd game fully published. The first was just diving in, this one was about building the beginning of the foundation. Went from 28%->77% usage on the $20 plan, but it was necessary. I'll explain below.
π
π
π
Day 1 of Claude Code
There's an inevitability happening in our industry that we can't ignore. AI is everywhere so how do we adjust as game devs and still respect humans. I have some ideas, but I have to learn first.
Published after my 1st literal 24 hrs in Claude.
Day 10 of UI/UX Skills
Sooo with that framework revelation was making sure my MegaGrant demo was accessible through a walkable pad. Sooo here's that. You can leave and come back easily.
I also realized a thing, so I'm making some framework upgrades to show off said thing.
Day 9 of UI/UX Skills
Had a revelation the other day that my framework was actually close to handling what I need for UI demoing. So committed to some framework upgrades to be able to walk onto a pad and show the UI only while on the pad, and dismiss the UI with a button.
I've seen all these posts on AI games made in a weekend or a week...
Where are the AI games that have been running for 6+ months that post about their dev experience? Can anybody point me in that direction so I can study the longer term value of AI? Cuz I don't see it yet π
π
π
Day 8 of UI/UX Skills
Learned a lot by adding this frame. Lots of little lighting and shaping tricks. I started to freehand without the tutorial near the end to start creating the effect I wanted. Really starting to feel the understanding. πππ
Open for Verse/UI work
Day 7 of UI/UX Skills
Going through tutorials to build my knowledge base. The goal isn't custom quality yet, it's committing time and building knowledge. Using AI just for asking questions.
Invest in your own skills, with AI for assistance.
This is a Candy Crush button πππ
Day 6 of UI/UX Skills
Spent the day researching and learning about variants and making a component with settings to tweak a button with various properties. Will be useful in the future. So much to learn.
Looking for potentially a 6 month contract for Verse/UI work folks πππ
Day 5 of UI/UX Skills
Sooo getting into the actual art side of things. Never been an artist, but I feel like UI is more mathematical so it'll be easier to build the skills.
It's also responsive!!! WOOHOO!!
Still on the hunt for commissions in Verse+UI, hit me up folks πππ
Day 4 of UI/UX Skills
Pushing the boundaries a bit and focused on the generation of variety for widgets and how to go about that in the future. Each feed now has options/combinations.
Next up will be creating something from scratch in Figma. Excited to get into it! πππ
Day 3 of UI/UX Skills
If I'm going to demo consistently to get commissions, I needed a better system. Inspired by the UI template, I've setup a demo room, and adjusted the Scene Graph feed components to be modular to show off one UI piece at a time or as many as I want. πππ
Day 2 of UI/UX Skills
Working on the ability countdown using a timer widget from Epic. Created a new material that does the math/texture with a duration/progress. Closer... need to add a colon still and add it to the widget fully. Getting there πππ
Open for UI commissions










