My background is in building web apps with Elixir and Phoenix. I made GG Translator in early 2024 to see if I could build a desktop app in a language I had never used before (Rust) with the help of AI. It was a great exercise and I found out that I could. I used Tauri instead of Electron because it has a smaller footprint. I built the app but never released it because I wasn't ready to support it.
When GPT 5.6 came out earlier this month I pointed it at the old codebase and tasked it with rewriting that entire app (still in Rust using Tauri), modernizing, refactoring, and looking for any improvements that it could find.
---
The app is a sneak peek of how an AI profanity filter might look like in the future. The ultimate integration would see it built into gaming platforms like Steam and PSN where it's not only transforming your speech on demand, but it's also able to transform incoming audio from your teammates into family friendly language so parents can feel better knowing their kids aren't being bombarded with slurs when they let them play online multiplayer games.
I also imagine an incredible opportunity for voice licensing allowing users to pay to unlock voices of their favorite streamers, actors, athletes, and characters for a limited time. Who wouldn't want to sound like Samuel L. Jackson yelling about motherfucking noobs in their motherfucking lane?
---
The biggest obstacle was code signing. I went through all the hurdles in 2024, paying for an expensive OV signing certificate and also paying for the Apple Developer program. For 2026 I decided that the OV signing certificate is a racket and I'm not going to pay for it again. I already have an Apple Developer account for another app so I didn't have to pay extra to sign the macOS build. For Windows, the SmartScreen warnings when installing the app are a drag, but you can just tap more info and install it anyway.
It landed me with a usable KDE environment with acceleration, but sleep mode resulted in an unrecoverable system without a reboot and the graphics driver had oddities like garbled screens during login and occasionally crashing the system if I opened the wifi settings. At the time I tried switching to older proprietary nvidia drivers and some other possible solutions for sleep issues, including asking an older GPT model at some point to investigate the system, but they were dead ends - it seemed to simply be an issue of unsupported old hardware, and I don't have the time to learn driver dev.
But when 5.6 Sol came out and I tried it on Ultra, I was struck by how capable it seemed, so I figured I had nothing to lose throwing it at fixing my system by any means necessary - worst case I would reinstall.
It did its work and went through a series of reboots, asking me to come back with what happened and occasionally do things like test physically closing the lid. I only had to hard-power off one failed kernel launch (which was initiated in some way that GRUB defaulted back to the old proven kernel on successive boots).
After a few hours of this, I found myself with fully working graphics and power states, with some nice bonuses like the time to sleep optimized near the 10 second warning limit (it wanted to keep going but I wasn't too worried about it) and the power options exposed properly to the KDE battery app.
I don't have the kernel dev background or time to learn it to audit all of this myself to submit patches to the kernel, but anyone who does is free to do so. I hope it can help someone else with the same era hardware.
Check it out: https://lexicon-writer.pages.dev/ MIT licensed. Repo: https://github.com/AashishH15/Lexicon
Please let me know what you think of the app!
This project grew out of curiosity. Loved the https://monster6502.com/ project but that is on another level. Here I tried to stay "reasonable" and added a Raspberry Pico 2 W on the back to drive it all. But also, was curious if Claude could pull this off. Guess I will have to place that order to call the cards.