In this episode of the Ruby AI Podcast, hosts Valentino Stoll and Joe Leowelcome AI and Ruby expert Chris Hasinski. They delve into the benefits andchallenges of self-hosting AI models, including control over model updates, costconsiderations, and the ability to fine-tune models. Chris shares his journeyfrom machine learning at UC Davis to his extensive work in AI and Ruby, touchingupon his contributions to open source projects and the Ruby AI community. Thediscussion also covers the limitations of current LLMs (Large Language Models)in generating Ruby code, the importance of high-quality data for effective AI,and the potential for Ruby to become a strong contender in AI development.Whether you're a Ruby enthusiast or interested in the intersection of AI andsoftware development, this episode offers valuable insights and practicaladvice.00:00 Introduction and Guest Welcome00:31 Why Self-Host Models?01:28 Challenges and Benefits of Self-Hosting03:14 Chris's Background in Machine Learning04:13 Applications Beyond Text06:39 Fine-Tuning Models12:27 Ruby in Machine Learning16:06 Distributed Training and Model Porting18:22 Choosing and Deploying Models25:19 Testing and Data Engineering in Ruby27:56 Database Naming Conventions in Different Languages28:19 Importance of Data Quality for AI18:03 Monitoring Locally Hosted AI Models29:37 Challenges with LLMs and Performance Tracking31:09 Improving Developer Experience in Ruby31:45 Ruby's Ecosystem for Machine Learning32:43 The Need for Investment in Ruby's AI Tools38:25 Challenges with AI Code Generation in Ruby43:35 Future Prospects for Ruby in AI51:26 Conclusion and Final Thoughts

Ver todos los episodios