wasi0013
Joined 12 years ago
Karma
727
Submissions
95
Member since
Jul 24
https://hellowasi.com
View on Hacker NewsRecent submissions
Comment · 1 year ago
Experimenting with various AI models via GitHub Co-Pilot on an extremely niche project to see how far these models have progressed. Used like ~60% of the premium quota to develop the following projects:
website: https://murajah.pages.dev/
Play Store: https://play.google.com/store/apps/details?id=com.murajah.we...
Manual audio splitting tool for the above project: audio-splitter-6b3.pages.dev/
I've always been skeptical of AI-generated code. This is my first experiment with AI agents, where the full code base, implementation, debugging, and deployment are done using AI Agents MCPs.
Used VS Code all the way, i.e., all the source codes, including the code to generate the Google Play Store APK. I only reviewed the source code before committing and helped debug by suggesting ideas/algorithms.
Mostly used Claude Haiku 4.5 like 75% of the time, where it failed, switched to the sonnet 4.5 or GPT 5 codex. Interestingly, when debugging, sometimes one model struggled even after numerous iterations/feedback loops, but then the problem was solved instantly as soon as I switched to another model.
The source codes are available here:
https://github.com/wasi0013/Murajah
https://github.com/wasi0013/audio-splitter
Initially, I thought the audio splitting could be done automatically using some AI models from Hugging Face or Whisper. But the audio files have some complex repetitions; the output was miserable.
So, for now, this splitting is done manually using a Web UI (The audio splitting tool splits the large audio files into multiple small audio files, think of it like a long paragraph is split into multiple sentences.)
I will attempt again to automate this splitting task using AI, after drafting a game plan for tackling the challenges. I'm thinking of using energy drops and other similar factors to create segments.
Comment · 1 year ago
Thanks for sharing my article!
TL;DR: My Obsidian Zettelkasten vault grew beyond 6,000 notes, and the graph view couldn’t handle it. It would freeze whenever I zoomed in to find subtle cluster of notes.
The graph view is valuable for spotting hidden relationships, connecting ideas, and turning scattered notes into something useful. In this article, I share my experience and a workaround using an alternate browser-based visualization tool which is working great so far.
Comment · 3 years ago
Yes, Outside of US. No, not using Firefox. VPN has little to no effect, when it happens. I even tried their own product cloudflare-wrap. It makes things worse sometime, which is an irony.
Privacy pass needs to be configured/enabled on the website's end or zone, no? I'm somewhat skeptical on using such extensions, I would rather avoid going to the websites unless it's a necessity.
Comment · 3 years ago
https://hellowasi.com/blog
I don't post much and if I do it's usually about programming and tech.
Comment · 4 years ago
Oh! I almost forgot it is worth mentioning the creator of Elixir Language "José Valim" also solves these problems and streams them on twitch [0].
Those are helpful to learn different approaches to solving these problems.
[0] Github: https://github.com/josevalim/aoc
[1] Twitch: https://www.twitch.tv/collections/k_DLnk2tvBa-fQ
Comment · 4 years ago
Wow, this is so cool! My goal of this year is much more simpler. Hopefully this year, I will solve all of them using a Functional programming Language named Elixir [0].
So far, I'm loving it! The source code is available on GitHub [1]
The repository also contains couple of mix tasks to generate boilerplate codes for each solve. And update the readme automatically on each commit to list the problems that I've solved so far.
[0] Elixir: https://elixir-lang.org/
[1] Github: https://github.com/wasi0013/advent_of_code