I've been working on a Persian classical poetry archive with LLM-generated translation. As a poetry enthusiast but a non-speaker of Persian, I wanted to read Rumi, Hafiz, and Bedil, but found myself jumping between ChatGPT and Google Translate. I sourced my data from Ganjoor, which was luckily available via their public API. Then I quickly put together a website with bring-your-own-key translation feature.
For now, there's no backend and it's hosted on GitHub Pages; it's a static website reading chunks from an sqlite-based DB file. I intend to change it in the future by running an LLM (preferably a frontier Gemini model, as works great for Persian) over the whole data set so you won't need a key to read the translated poetry. However, I don't have the budget of $1000-$2000 to spend on the tokens currently.
> so you won't need a key to read the translated poetry
This probably sounds like a crazy question, but if you are already getting translations using someone else's API keys, can't you just store/cache that response so that the next time the translation is requested, you already have it?
get a few personal gmail accounts's gemini API key, and you have 1000s of free LLM calls to flash-lite models, which are more than upto this task. one time run, and save it to your db.
I am a generalist software developer with experience in a broad range of technologies, from full stack to blockchain. I learn fast and quickly adapt. My recent gigs include working for a Norwegian startup as a Clojure and Smalltalk developer, writing smart contracts for a creative codes project, and designing and implementing a dapp for Internet Astronout NFTs collection.
I'm up for any job that involves solving interesting problems with code. Feel free to write me at muazzam_ali@live.com
The gotcha thing about this puzzle is sort of greedy approach; try to disentangle the local sub-graphs - concentrate on any nodes of your choice and their connections - and the global graph starts to fall in its place. It's trivial approaching it like this.
I'm no expert and can't examine all the bits in detail, however, I trust the likes of FSF and Stallman. So far, they haven't given approval to any laptop built after mid 2000s. I wonder why.
Points for creativity, but in my opinion this borders on rule-lawyering with not much benefit. The code that tells the ARM/M4 to load stuff from that SPI flash can be easily changed, it's in the bootloader, so it can change that code before putting it into the DDRC.
SEEKING WORK, Pakistan, Remote OK, Email: muazzam_ali at live.com
CS student at a top university, hobbyist developer for a long time, academic ML enthusiast. My last freelance project for NYC client involved building a screen and webcam recorder in C++ and Microsoft Media Foundation. Thanks to the memory-related bugs I encountered in C++, I decided to give Rust a go and loved it. In college, I took a semester-long Node.js and React.js course, so that's what I can handle on the front-end. For back-end work, I of course have a preference for Node.js, Rust, and Go but I'm a fast learner and can get started with any language in no time.
Yet another model that has probably been never used on high scale: letting people sponsor tickets (GitHub issues). The donation would go to the contributor who closes the ticket to the satisfaction of the main contributors. The amount, of course, will be decided by how a ticket is perceived as important.
The same reason Facebook loads multiple MBs of JavaScript code for something that could have been not more than 1 MB. One can't help but wonder about nefarious purposes: either collecting user data or abusing the computing resources. For companies that tend to hire the best and the brightest, the 'software bloat' theory is not compelling.
Curiously, major Linux distributions have also gotten significantly slower compared to early 2000s versions.
I wonder, for a thought experiment, what if companies stopped development on software when it reaches certain stage of maturity, say Windows 2000, providing only necessary security updates or optional visual changes?
I was very reluctant switching from win xp to win 7. Unless the 64bit era would have forced me I rather would have stayed put.
New software is really not adding much to the table after some point of completion since the software companies seems to mostly add pet feutures and user hostile fads be it star menu, complete gui changes, 'enterprise' admin lookout or ads and tracking.
E.g. Facebooks 1000s of developers seem to add a net of antifeutures to their site. On Netflix you can't even disable autoplay.
It is the same really for software moving to remote mainframes. The companies rather hide and burry the old desktop versions deep.
For now, there's no backend and it's hosted on GitHub Pages; it's a static website reading chunks from an sqlite-based DB file. I intend to change it in the future by running an LLM (preferably a frontier Gemini model, as works great for Persian) over the whole data set so you won't need a key to read the translated poetry. However, I don't have the budget of $1000-$2000 to spend on the tokens currently.
Website: https://0x5ce.github.io/farsidaan
Code: https://github.com/0x5CE/farsidaan
P.S. Contributions welcome.