Developers have long prided themselves on pure local workflows (“it works on my machine!”), but AI-driven coding can throw a wrench in your offline setup. In this session, Roberto Carratalá and Kevin Dubois show how to keep dependencies, latency, configs and costs under control—even when you’re tapping into cutting-edge AI.
You’ll learn to run models on your own hardware, experiment with different code assistants, weave local AI directly into your apps, and compare vendor models of various sizes to hit the sweet spot between speed and accuracy. Plus, get a straightforward pros-and-cons guide to choosing local versus remote AI so you can optimize your dev flow and functionality.
Watch on YouTube
Top comments (0)