VRAM vs System RAM: What Actually Limits Running LLMs Locally?
If you’ve spent any time experimenting with running large language models locally, you’ve probably seen guidance like “you need 30GB of RAM” to get a model w...
Recent Posts
llms.txt: Robots.txt for Docs in the AI Era
Your docs are training AI models right now. Here’s how to take control.
The Principal Developer Advocate Paradox: Scaling Impact Without Burnout
As a Principal Developer Advocate, you don’t own the roadmap, control the pipeline, set budgets, or dictate campaigns—yet your work influences all of them. Y...
Hosting a (DevOpsDays) Tech Conference
In August 2024, we pulled off the first-ever DevOpsDays Halifax, and wow, what an experience! As one of the organizers, I’ve got a ton of stories, lessons le...
Connecting the dots: Let’s get ship done!
Today I’m joining Harness as a Principal Developer Advocate. Harness is a complete software delivery platform whose mission is to enable the 30M+ software de...