duck_master

Update: After manually transpiling @karpathy's code from JS to Python (and re-architecturing some of it along the way), I have a functional code draft [here](https://github.com/duck-master/TWAAH-updated). If you run it, it...

Another update: I've implemented the first two things and placed the output in an actual file. The result is [here](https://raw.githubusercontent.com/duck-master/TWAAH-updated/main/twaahu-draft1.txt). Tomorrow night I'll get to working with GPT-2 and continuity....

Third update: It looks like GPT-2 is unexpectedly difficult to work with. Libraries I've tried: - gpt-2-simple, which initially failed to work. Following [this Medium article](https://medium.com/@stasinopoulos.dimitrios/a-beginners-guide-to-training-and-generating-text-using-gpt2-c2f2e1fbd10a), however, by downgrading TensorFlow...

Fourth update: Got GPT-2 to work from terminal, but mysteriously not from shell.

After much reflection, I've decided that I want to declare this finished. I already have an output of the required length, and GPT-2 is pretty hard to work with anyways.

Eureka: I've scraped my first tweets! Now all I need to do is to automate doing that a bunch of times. See picture.

I changed the type of the project because Twitter was doing rate-limiting thingies. Now I'm using a fixed corpus, which is the Russian troll tweet database available at [http://nodeassets.nbcnews.com/russian-twitter-trolls/tweets.csv](url), and...

I also ran into this when trying to install webcrack on node v24. It worked when I went to `nvm install 22` though. Here are the logs I got (but...