308 karma · joined May 25, 2012
Reverse engineered an old audio recorder USB driver which only works in windows 7 and also reverse engineered the custom audio encoding the device uses and the software to convert it to a standard wav file. This took recording the USB traffic with Wireshark for each function in the original software in a VM then disassembling the various dlls and exes and driver files and feeding them into Clause step by step.
That AI button in DataDog not only diagnosed the problem across micro services but also created a fix PR. I think we might be unemployed soon.
Also find doing it like this either incredibly hard or have to do a ton of git magic after I'm done to get commits into this state which is very frustrating.
I think it might be the codebase I work on but who knows.
Look at what other people in your community did or ask them. As someone who left a developing country I would say get a degree any degree really and then get a job and some savings, you can then apply to a masters program abroad, a lot of countries this will be free with or without scholarships you might even get a stipend. EU especially.
"Document Too Long Document is too long to process. It contains 158 chunks, but the maximum is 256. Please try again later or contact support if the problem persists."
Yandex browser does the most impressive version of this and for free but only to Russian I believe, its quite amazing it does appropriate different voices and follows the correct intonation for everyone, just takes a few seconds for a YT video.
I think you can look into muting the original voice in the video, I remember I saw there is some AI/tech that can separate audio into voice and nonvoice.
Yandex browser does this in the browser, you open a YT video and it offers to translate, a few seconds later the voices are all in Russian, it's probably the most interesting production use of AI I have seen and for free. It's to Russian only unfortunately.
Amazon has indicated that they are creating their own TV OS in Rust running ReactNative Apps and going away from Android although it might take a few years.
It would be nice if they could layout what exactly is missing in terms of data to make a language work better, while the actual AI bit is out of reach for most of us maybe we could provide more data.
There is also a 60 sec limit and wonder if this is HuggingFace limitation or Seamless?