AI Coding: Key Considerations around Models, Hosting, Security & More - Video

When coding using AI, there are so many options to choose from, including just typing your questions into ChatGPT and using the model for continuous code completions and suggestions. However, the underlying issue is understanding what options are better - should you use a general purpose model or one specifically trained to your language? Should you host them locally, in server farms, or with the providers?

Chapters:
00:00 Introduction
02:00 Is larger models always better than smaller models?
05:01 Fine tuning models
07:41 Can models be trained to learn multiple languages (say C++, QML and SQL)?
09:35 Why are Apple laptops better for home tinkering?
11:48 Are there cheap options?
12:45 What is a token and how fast do I use them when doing code completion?
18:44 What kind of models do we have available?
21:10 Will my code be leaked, and what code is uploaded to the model?
24:37 Foundation models versus fine tuning

All videos from "The Curious Developer" series: https://youtu.be/nQPumFkN-Ow?list=PL6CJYn40gN6hJTctPIDqLciH9E_PoIklY

All videos about AI for Coding (with Qt and beyond): https://www.youtube.com/playlist?list=PL6CJYn40gN6gxKdn6HK3CYqPo4B3JxKSz

Please note that non-English dubs for all KDAB videos are auto-generated. These translations have not been moderated by us and may contain inaccuracies. We appreciate your understanding and apologize for any confusion this may cause.