Intro to Generative AI and LLMs Workshop
Our first workshop on generative AI, on 9 March 2024. The idea was to understand what is behind large language models (LLMs), try real tools and leave everyone wanting to build something of their own.
- Talk video on YouTube (in Spanish)
- Workshop resources on GitLab
Generating images
We compared three tools:
- MidJourney. The best image quality and easy to use from the web. In exchange, little room to customise and the odd strange glitch.
- Stable Diffusion. Open source and runs on your own computer, so your data stays at home. Highly tweakable, with a huge community behind it.
- Leonardo.ai. A website built on Stable Diffusion, free with credits that renew every day. Good for playing around without installing anything.
Language models
What an LLM is and how to use one for everyday things, like translating text or coming up with baby names. We also saw how to run models locally with Ollama, so you control both the model and your data.
The speakers also showed their own projects: conversational interfaces and creative content generation.
Ideas for future workshops
At the end we talked about what to do next. Ideas included Jarvis-style personal assistants and AI home automation, plus workshops on programming, Arduino and PCB design with KiCad.
To keep going on your own: YouTube channels and communities about generative AI, and plenty of GitHub, which is where the projects to tinker with live.