I’ve used spicy auto-complete, as well as agents running in my IDE, in my CLI, or on GitHub’s server-side. I’ve been experimenting enough with LLM/AI-driven programming to have an opinion on it. And it kind of sucks.
I use local models, and it barely doubles the electricity use of my computer while it’s actively generating, which is a very small proportion of the time I’m doing work; the environmental impact is negligible.
Try a rubber duck next time. Also, diagrams. Save a forest.
I use local models, and it barely doubles the electricity use of my computer while it’s actively generating, which is a very small proportion of the time I’m doing work; the environmental impact is negligible.