Events Section
Rework of my website is done! I’ve added more information about what I do on the events page. Instead of just using a timeline, now I just have a scrolling panel that shows all the different organizations I’ve been apart of.
Project page
Before, when you pressed learn more for the project blocks it just takes you to a Github link which is boring, and not informative on the projects I will make. So I added a whole other html page for that.
Filling out the rest of the sections
Doing something else with the event section because the timeline didn’t feel right.
Testing
I didn’t code much but I just ran my program across multiple days, and tweaked the prompt to make the categorizer more accurate. I think I’ve tweaked it to a point where it correctly categorizes daily activities done on a computer, and rarely gives a incorrect status.
I did some looking into prompt engineering, and I’m realizing it’s tough. Sometimes the AI, mistakes things I’m doing and puts them in the wrong category. Ex, if I had Discord open, and a friend sends me a video, the AI would mark that under doom scrolling, even though I didn’t do it. I’m also trying to keep it simple because sometimes when I tell it something specific, it thinks all cases should be considered the same way.
So I got it working!!! I tried it out in Discord for a few hours, and the AI usage limits is holding up well. I was about to switch to a different AI because there were usage limits, and I kept hitting it. I realized it was because I didn’t have to upload the images to the Gemini cloud. I just let my program read them directly. And I made it so it takes a screenshot every 2 minutes instead of 20 seconds.
So I started testing out the AI here because I’ve never worked with it, and it wasn’t as hard as I thought it’d be. I decided to use a Gemini API, which I had to get from the Google AI Studio API Keys page. Then they also had a page somewhere teaching you how to use the API, which helped a lot (Gemini API help). The biggest issue I had was which model of Gemini I was using. 3.5 lite allowed more usage, and was the latest model that I could use.
Check out the code below to see how my simple AI interaction works.
This is the start of a mini program I’m making that’s going to track my activities on my computer to give me an incentive to be productive! So below here I have a plan of what I’m trying to build, and it seems I’m going to have to learn about using APIs, communication between different local programs like IPC.
I’m not sure how to track the time I spent planning so I started a bit of code to log this.
I have to figure out what AI I could use, and learn how to incorporate a AI in a python script.
I’m calling it Nozi bot for now because it sounds like “nosy” and it’s like tracking what you’re doing for your nosy friends.
So I made new custom windows for the Inventory and trade windows in the menu. It’s crazy to see how far the UI has come.
I also fixed the crazy lag there was. Turns out, even when you are in the school, clouds, and buildings were generated in the back with the parallax effect. It was really process-intensive. I got rid of that and made it so the foreground stops generating when you are inside the school.
Also, I just want to say I created the custom windows myself using Kirta. The image above was like a quick mock-up.
I want to do a bit of code architecture rework because I made the base game with a lot of AI, and the code is really hard to manually edit, which I need to do a bit of. So I’m going to rework the code and turn a lot of the UI into classes, so it’s easier to implement things that are a bit more specific than the AI could manage. AI is ofc a good learning tool, and good at creating something that “works”, but all that inefficiency is catching up to me.
I made the layout for the events/ activities section to show (time - activity name - description). I also added a contacts sections because I think that’s important. So, almost everything is done, I just have to actually put down information about me now!
I got the project display system down basically. I can put images, titles, and a description for each project. When I click into it, I can make another page with more info! I also added a sticky nav bar on top, so it’s still easy to navigate to different sections.
I’ve finished the 3d models for the page navigation! And I finished the navigation system. Now I can click my icons to navigate to that section of the page.
Also shout out to @Max_, my layout was inspired by them 👍
I’ve wanted to make my own personal portfolio site for a while now, and I never got to finish it. Now I’m coming back to this project, and using new knowledge I’ve learned to create a new, cooler site!
Today I did some planning, and created a layout of what I wanted to build. I also started on the 3d model of the home page interactions.
So I didn’t like the basic buttons and UI I had. The game didn’t feel personalized, so I did some hand drawing and using a digital art program, I made some new UI to be placed into the game. This is only log #6.1 because there are a lot of assets in this game that I also wanted to rework. I spent a lot of time planning, drawing, and digitizing the Icons and UI, but the time logged is only the time it took to vibecode it into the game.
The focus of this log was to make the game more fun. New battle mechanics and features, and well as minor tweaks to either the sound system, or other sub systems.
So close to finishing!!!
The focus of this dev log is the introduction of the story progression system, and bring back the battle system. Now in addition to fighting randomly generated enemies, you can find special NPCs that progresses the story when you interact with them.
The image attached below shows some of the character NPCs, and some other menus you might see in the game right now.
This time I mostly worked on map generation, and player interaction with the environment. I ran into a lot of issues especially with the platform collisions. I had to go back and forth with the AI a lot to get what I have right now.
A picture with my planning is shown below along with what the game looks like right now on the right. I planned this out in Figma, it’s pretty useful for planning like this!