In part 1 of the hackathon I participated in at work, I set up the GPT4-x-Alpaca LLM with Oobabooga in an AWS EC2 instance. Next up in my hackathon journey was an attempt to make the LLM do something useful and fun. I’ve been casually interested in creating a Multi-User Dungeon or MUD for short. So for part 2 of the hackathon, I dug into the documentation for Evennia, a Python-based MUD game engine.
Ever since ChatGPT hit the scene, it seems to be all that anyone is talking about. I participated in a hackathon at work last week and was able to spend some time playing around with Large Language Models (LLM for short). Specifically, I was looking for something that could be hosted locally and did not communicate with the internet. ChatGPT is great and really useful, but most companies are not eager to share their private documentation or proprietary code in a public AI chatbot.
Earlier this year, there was finally an opportunity for another hackathon at work and this time I decided to try to build a game in a week. I’ve been working a bit with Godot, the open-source game engine that’s been growing in popularity recently. My experience has been that it’s fantastic for the 2D games that I usually fiddle with and it is also more than capable of handling 3D gamedev.
When I attended AWS re:Invent at the end of 2019, I attended a workshop for using machine learning via Amazon SageMaker to teach an AI how to play blackjack. Seeing as re:Invent was held in Vegas, I decided to take the spirit of Vegas home with me and create my own text-based blackjack game in Go. I added a simple interface so it would be easy to create different AI opponents.
This is waaaay overdue, but we had another hackathon at work back in September of last year and even though I’m waaaay behind on blog posts, I wanted to make sure I did a short writeup on my project. During Gophercon, I received a small Arduino Nano 33 IoT. Not exactly a powerhouse, but I wanted to do something with it. I bought a breadboard, sensors, wires, and other various components.
We had yet another hackathon at work. This time around, I wanted to do something with Python. Since we have a gap in test data at work, I decided to create a script to generate oodles of fake test data using a Python library called Faker. It has a number of default providers for generating different types of data. It can generate fake addresses, names, dates, phone numbers, etc. This simple code block:
When the theme for our latest company hackathon was revealed to be “Need for Speed”, I went straight to Best Buy after work and picked up a DJI Tello drone. I had been wanting one ever since I went to Gophercon and saw the presentation by Ron Evans where he used Gobot and GoCV to make a Tello drone follow his friend’s face around. Now that I had a drone, I needed to figure out what to do with it.
A couple weeks ago, we had another hackathon at work. This time, I wanted to create something useful that could potentially be adapted by one of our teams. My initial thought was to convert some of our old C++ code to Go and remove a Windows dependency, but after talking with one of my coworkers, we decided to instead create a DNN service for executing a Caffe2 model in Go. We had a third volunteer join us and we set out to achieve our goal.
Recently, I had the pleasure of participating in an internal hackathon at work. They gave us two days to create whatever we wanted with whatever group of coworkers. There were no specific guidelines on what the project had to be or what technologies it needed to use, so I decided to go solo and recreate Conway’s Game of Life in Go. I’ve been fascinated with the Game of Life ever since I first heard of it several years back.