@Stv120

Devlog #8
I did not think this devlog was needed but apparently it is very much needed.
This is mostly for the people that will rate this and the ones responsible if my projects gets thru.
First off, I gotta say the reviewers are another kind of human species. If you want to rate something, actually rate it and put effort, BUT if you come here review it and conclude “heavy AI usage” from a technical menu and a thinking bubble thats part of the UI, you probably never used an app and got stuck in the 1980, where people used the console to communicate with the computer, because how do you conclude that just from UI???? Thats for my last reviewer who said I used and I quote “heavy AI”, mind you he had the other devlogs to check out, what he only did was review the UI, and 0 code, none of it was code! Okay he did underline some stuff tho that tought was AI, and guess what? It was, YES, what a surprise, a 16 year old USED AI? Well thats shocking. Seriously, do you expect a 16 year old to make a language model all by himself? Some of that stuff you do in 3rd year in university, but I guess this platform is made for only top 0.1% teen coders! This hackaton rates just the final product, rather than the effort. I could put as a project a game that competes with AAA games and there will be people leaving minimum effort ratings saying it is not good enough, probably nothing is good enough for this problem. Sadly I wish you could report reviewers who dont approve ur project from reasons that make no sense! Second, my second last reviewer said my readme was made with AI just because I used “-”. Seriously? Just because AI overuses that character does not mean everyone who uses it used AI for all of it. And guess what? I used AI for the readme too. But not at that part (because apparently using more advanced english or symbols you dont really see, its AI. No. It just means there are people who know how to use the keyboard ), I used it to write the commands for people who want to build the project on MacOS and Linux, and I am 100% not required nor its the bare minimum to make it for those 2 OS. Not even all big companies make their software for Mac or Linux, yet you expect a teen to do it? Pathetic if you ask me. And third, thats about it, the ones who keep saying “web support”, well thats very funny. Because, no, im not writing my project which i spent hours out, because u dont have the effort to download it. I swear where do yall come from? Is your birthplace the Linux kernel? Im sorry but if you code from infant age, does not mean I should deliver top quality, if you want a top quality software, you can go rate the big companies who make overpriced software. If these reviewers actually reviewed stuff that matters way more than a fun hackaton we would live in an utopia. But sure if you want to keep touching the terminal, not grass, and live ur coding life, be my guest! (All these apply for the ones who think teens should be ready for a Microsoft interview! If you dont want to rate this or dont have the energy to, just skip, it helps me and your busted brain!)
PS: atp this is cyberbullying gng get a grip 🙏

Devlog #7
Hello guys! This is probably my last devlog before releasing this project, and I want to share what happened during the last 3 days.
Also, keep in mind that I previously had a version based on a Q&A-type database that I had generated using an LLM.
First off, the version from the last devlog was based on a database from DailyDialog. It was very heavy for the model’s “brain”, and as a result, it wasn’t really able to communicate properly. It would sometimes respond with something completely unrelated to the question.
After that, I tried training it on a Wikipedia dump. As an idea, it was good, but the amount of time it took to finish a training session with 30 epochs was LONG. And even after that, the AI still wasn’t capable of having proper conversations.
After that, I asked ChatGPT for help, and I can say that ChatGPT is not only bad, it is horrible for debugging. It makes stuff up, changes things that aren’t even broken, and generally makes the debugging process harder.
So I tried using Claude. Claude at least tried. It actually computed the project on its server, fixed something, but it still wasn’t enough.
Then I discovered Codex. It’s not entirely new, but I didn’t know about it before!
I gave Codex the project files and asked it to search for the problem. It gave me the files back, and it actually fixed the problems.
When I tried the fixed version, I asked it some questions. It had been trained on both a Q&A database and a Wikipedia database, and it actually answered correctly most of the time.
The problem was that when I asked something that wasn’t in the Q&A database, it retrieved information from the Wikipedia dump. That wasn’t necessarily bad, but it didn’t know how to actually make a sentence using the information. It was basically just a retrieval tool rather than a conversational AI.
Since my Codex tokens expired and I can’t use it for a month, I didn’t bother continuing with that version.
I went back to the version from before the last devlog, which was based on a smaller Q&A database. I improved the database, retrained the model, and now it actually responds.
The problem is that if you’re not using proper grammar, it can still respond with something unrelated to the topic. And if the topic isn’t included in the database, it can make stuff up.
After that, I added an Ollama version alongside my trained model. This way, if the user wants an answer that my trained AI can’t provide, they can use the Ollama model instead.
I also made a UI with the help of an LLM.
So now the app is functional. Both models are available.
I also thought about adding a tool to my trained AI that detects when the user wants math support, but for now it would only be for math and not other topics, so I’ll see if I end up adding it.
About web support
I don’t think I’ll add a web version since the UI is made using PySide6, and making it web-compatible would basically mean rewriting the whole UI.
Or maybe there’s an easier way to do it that I don’t know about.
Linux and macOS support
Linux and macOS support is possible, but I don’t have a Mac to actually test whether the program works properly on that platform.
Linux should be easier since I can install a Linux distro in a VM and test it there, although I’m not completely sure yet.
And that’s basically where the project is right now.
If you have any suggestions leave them in the comments, thanks!

Devlog #6
Hello guys!
Yesterday I realized what was the problem with the language model and its predicting. So basically I was testing it by typing “Hello” without punctuation and so the AI was confused and did not know how to respond, hence the unexpected responses. When I tried with the word “Hello.” with the dot it did work! And besides this problem, I also encountered another problem. The AI couldn’t recognize, even if the word was in the training.txt file, if it was spelled wrong or had capital letters or not where it should have been. For example I asked it “What is EArth?” and it returned nothing because it did not recognize “EArth”, in its vocabulary, so last night I sampled a training text in json format from DailyDialog dataset, made a converter.py file, which extracted the dialog from train.json . I ran 3 epochs because the new text contained 2660291 training examples (WHICH was WAY WAY bigger than I expected!), and it took like 1,5 hours to finish. After that I tested it and again, the model predicted the answer wrong so now I upgraded the embedding size from 32 to 64 and ran again train.py (currently it is still training!) . Anyway, if it doesn’t work again I will probably look into the configuration again, maybe upgrade the epochs from 3 to 6, since the other major components like main.py model.py and train.py are fine (probably). I attached below the training progress

Devlog #5
My brain is soup currently. I have made real progress, at least, at least… . Now the AI is trained on my CUDA cores from my GPU. And now it can actually make a conversation, which is WOW, but the thing is… the responses are not consistent or they do not make sense, but at least they are words that can be understood separately. I have also changed train.py, model.py and main.py multiple times, upgraded to training.txt file which now contains multiple conversation examples, but the project is far from over. I attached below how it responds currently. If it weren’t for the 10 hour devlog limit I would’ve kept going.

Devlog #4
Hello guys!
• I finally rebuilt the 3 biggest components of my AI, those being main.py, model.py and train.py, completing a solid foundation which can be upgraded from now on without the need of deleting the current code completely.
• Anyway, currently the text sample which it is being trained on is not too big, so it can’t “learn” much, and the context right now is just “Hello wo”, and it predicts the next character right as intended, using the last 8 characters
• The first changes I obviously need to make are changing the context from that to the input of the user and making the training sample bigger, then we can move to upgrade the epoch number from 100 to lets say more and the context size from 8 to more characters. I will announce my plans for the future upgrades in the upcoming devlogs.
• Here are some previews of the code and some notes I took: (if they all load correctly hopefully)

Devlog #3
Hello guys!
I am working so the program will be based on an 8 character architecture, meaning that it will now predict the next character using the last 8 characters, not just the last one, meaning its brain gets upgraded! I am still learning how to do an AI at home with the help of YouTube tutorials and AI so it will take many hours to finish, but my expectations for the final product are high!

Devlog #2
Hello guys!
I have updated main.py which tests the AI, train.py, model.py and tokenizer.py and I reached a milestone since the AI now predicts what letter comes next. Right now it is being trained by a pretty simple text file but I’m planning to upgrade that too!
Here’s a quick preview:

Devlog #1
Hello guys today I am working on a project with the goal with building my own AI, yes, you heard that right! The goal is to train it locally and that it works 100% offline
Here’s what I did up until now:

1. I set up the project in python
2. Built my first neural network with the help of AI that contains one neuron and which was used to understand weights, loss, prediction and more
3. Did my first AI training which the AI discovered the multiplying by 2 rule
4. Dataset loader
5. Tokenizer
6. Custom vocabulary
7. Encoder/Decoder and a few other stuff

Hello guys!
The project is finalized I just have to upload it to Git!
I have added hidden easter eggs, sound effects and more!

Hello guys!
This is probably going to be the last devlog before I publish this project! I know it took way longer from last time, but the final version will include, like I said last time, some easter eggs that change how to app behaves
I have improved things from last time such as:

1. Made the user experience better by making the code more efficient and fixed some bugs
2. Added an error and click sound effect
3. The buttons now turn light grey when the cursor is over them and dark blue when holding click

I hope you are excited for its release!

Hello guys!
The calculator is fully functional, yet not ready to be released!
I have added a functional text box and buttons which calculate the specific function of the angle, but I will work on making the code shorter and cleaner, optimizing it, interactive buttons as in when u button is clicked it will change color and some easter eggs that change the GUI and/or how the app behaves

Hello guys!
I am working on implementing text boxes into this GUI version of trigonometric calculator!
For now I am testing the buttons if they are clicked or if the mouse cursor is over them (probably going to add mouse hover later)

Devlog #2
Hello everyone!
I’ve started to work on the new version of the trigonometric calculator which is made using raylib
Here’s what I’ve done:

1. Created a window 800x450
2. A box where the user can enter the angle in degrees which a trigonometric functions is applied to
3. Buttons that display the function which the user wants to apply
4. A rectangle which shows the result

It won’t take much time to be published, expecting it will be ready to be shipped in the following days!

Hello guys! As its my first devlog I want to mention I am currently working on multiple projects one of them being the trigonometric calculator which calculates either the sine cosine tangent and cotangent of a given angle in degrees. The project is still in the console version, but I’m developing another graphical version which will be made using raylib!