Hey! I’ve made some more fun updates. :D
I mostly fixed some bugs and introduced some other fancy icons and a new menu! I’m working on UX things largely. I’ve come to the unfortunate realisation that my current algorithm (despite being fun to watch) isn’t very smart when it comes to multiple obstacles. I’ve had to limit it to 3 obstacles…

HOWEVER!

I’m OFFICIALLY ADDING ANOTHER ALGORITHM! A more complex one. I’m planning a Q-learning algorithm. I currently don’t really know how to code one, but that’s what I plan to figure out over the next few logged hours! I plan to alter the home page to be a selection menu. The ‘recommended’ option (Q-learning) and the fun option (genetic algorithm).

I really hope I can figure out how to make this work properly, as I think it’d be a super fun improvement. Naturally, I’d have to limit it to a grid-based game, but I think that can also be fun! I’d love to hear what you think! :)

Also, this devlog is 1000 characters EXACTLY! Check for yourself.

Added a start menu. Working on improving it with labels. I also improved the icons and AI logic.

Haven’t coded in a while!
I also added the obstacle dragging system and the other things I planned to add in my previous devlog! :D

Updates!

Finished the algorithm! It is much smarter now!

Optimisation

I didn’t copy-paste any code, but I asked Claude AI to help me diagnose the main issues. I learned how Svelte’s reactivity is done, and now I know a lot more about handling arrays and DOM updates efficiently! :D

I learned to use {#key} in Svelte, which triggers updates upon a change in the selected variable, which makes 100 updates per frame, (6000 a second) into 1 per frame! It only updates when needed.
There are a few more optimisations

Plans!

I plan to add, like the rounding of the “curiosity” variable, since it’s converting to a string each update, which is quite inefficient. I wanna make it stay a number. Also, I should REALLY start adding comments. Maybe using key-words for each part? That would help me find certain things. Coding using these indices and arrays can be quite inefficient. ONE more thing, you can see the art I made for the bee in the image below! If you don’t like it, please say so. I don’t know if I should keep it.

PS, I write all the devlogs, descriptions and READMEs by hand (no AI), so I apologise for any spelling or grammar mistakes! :D

Improved learning algorithm!

I spent a while optimising the algorithm in various VERY effective ways! The agents respond well to distance from the target, and very well to arrival! I’ve also added a simple, small button panel for the user to change training values! I also added a curiosity and speed parameter.
In the image below, you can see the agents learning to navigate around the obstacle to the target! I’m next going to improve graphics, adding cute icons and sprites, theming the site around bees going towards their hive!

Started implementing AI algorithm. Using a genetic algorithm! Trying to figure it out. :D
The AI currently chooses a pre-determined set of random directions, and whichever one does best is recorded. Then, the others receive its genes alongside a randomiser so they don’t directly copy it.

Made the site mobile-compatible - allowing for even more people to get rage baited. :)
I also fixed a few spelling and logic errors and added a backspace button.

Made a calculator! It spits out whatever is entered. It’s mathematically correct, so… :)
It also requires you watch a 10 second ad to calculate something. If you want to clear after that? Just buy premium! How do you do that, you ask? Simply press the button 100 times to confirm, but - oh no! You need premium+ to get premium. Just scroll to the bottom of the (VERY LONG) page, and see…. Oh… (see for yourself! XD)
I personally think I’m hilarious hehehhehehehehe

Shipping soon! Fixed a few things. Animations on WebKit didn’t play properly, but I managed to fix that after a while. Also, improved scaling logic for the top bar. I also experimented with Tauri releasing, but decided that the server backend was not worth the time it would take since MacOS releases are niche for a web-tool. :)

I added a simple loading indicator (with an animation) that displays both when the site loads and when the AI replies.
I improved and improved the clarity of the server error message. I also improved the logic regarding the user input bar to make it feel cleaner and quicker.
I fully rewrote the system prompt to make it more secure and efficient. Pretty productive hour! :D

Made security improvements to counteract the prompt injection vulnerabilities. Also limited smaller models to avoid invalid JSON.
I also tried using the HackClubAI, but for the models I used, the advantages weren’t worth it for responsiveness. I’ve reverted that change back to Groq. I plan to use it in future projects though! I made a few other bug-fix changes too.

Saving update

I added a saving system! You can simply clear the chat as usual, but now it stays on reload! Also, I added the ability to customise the context window within settings, and added an about page to learn about the app and unique features.

Image UPDATE!

I added an image system that lets the AI show the user stock images as needed.
I also added a system for changing models. I’ll add more models later on.

Devlogggg!

Added a settings page with temperature control. Added a nice animation when text appears. Added a custom 404 page, and finally, fixed various bugs and improved the input box. :)

Added some improved logic for the dark mode. No longer flashes white initially.
Added a nice fade-in animation for the text.
Also fixed the visuals of the new input container. It now centres it better. :)))
New devlogs soon! I will probably ship in under 10 more hours of work.

ANIMATIONS

I added some fancy animations and improved the input box!
The animations apply to all buttons and other elements. On important buttons like the ‘restart’ and ‘delete’ buttons, they highlight white. On others they zoom slightly. The background now smoothly shifts.
The new input box allows for multi-line support!

Added a dark mode, improved UI, changed font, added new tables, new dividers (for the AI), new lists (bullet point updates), and new code blocks! Also MANY smaller changes, like colouring hyperlinks to fit the style.

Things to do:
Further improve list reliability and add more fun features!
Also improve the question UI.

Added auto-scrolling! Also fixed major bugs with displaying.
I added a better question system, and improved the system prompt.

Added question logic! It was a battle to get the AI to not do anything stupid, but I think I’ve (hopefully) done it! :D

First Devlog! Made a UI for the project and got my AI backend working! Really liking the design so far! First mock-ups were in Figma, but all photos are of my app.

I’m now going to try to add the question system, and then improve UI details like the top bar.

Many UI improvements! Switched build adapters, released project online.

HUGE backend update!

Fully overhauled authentication, including removing the timer-based update system replacing it with a better automatic one.
I also changed the data from a simple array to a better object.
I also made the ticking-off function global to fix issues regarding user updating upon another user clearing.

(note, the image linked isn’t accurate regarding the changes, as they’re all backend…

Added a username system, also altered the update times and added the ability to check items off the list. Also added a clear button.

Big updates!

UI Improvements, added code creation, added Settings page, added improvements regarding cross-device scaling, and more!

Liist

This is my first FireStore-based project! I tried earlier today and learned a lot, but felt as though I used too much Claude to do it, so I remade it myself (aside from occasional debugging, I’m still very new. XD)

I’m super excited about how it’s coming along. I’ve added a basic system of how it works so far! Just gotta update it to allow for various codes and such. :)

(PS, It’s responsive to other devices. XD)

Fixed more bugs! Also added weather to the newly named ‘dashboard’ screen!

Added a weather condition description after experimenting with capitalisation methods! Tested various forms of location detection, but IP proved simplest for the user and development. I also optimised the current IP system to not re-fetch each page reload, rather just saving it to the device. If changes are needed, they can be reset in settings - also fixing the city bug. Improved UI across various apps.

Some nice UI improvements, generally optimising the CSS code (removing double “rows”, etc) and a few other improvements like adding a date item to the home/time page.

Added a new “Dice” page, a few bug fixes and other improvements in the settings layer management.

Fixed IP Geolocation mixed-resource issue for weather app.
HTTPS website failed to get data from HTTP geolocation. :)

I added a weather app with IP-based geolocation and worked more on the UI, as well as optimising yesterday’s array mapping system, by simply renaming the variables. :)

First Devlog! I recently updated the app to its “Matrix” update - adding developer tools! :D