llm
8 artículos, del más reciente al más antiguo.
-
Quantization: Making LLMs Smaller Without Making Them Stupid
"Thanks for this explanatory article. I would like to read your thoughts about quantization: how it affects performance and/or how to select an appropriate one. I look forward to reading from you!"
-
VSCode Agents Window: An AI Harness Inside Visual Studio Code
Over the last few days I started hearing a word everywhere: harness. At first, honestly, I thought it was just another buzzword... But some colleagues at work showed me what an harness mean, by example, and just before I could taste one by myself (I had other plans for this morning than writing this concrete article) VSCode Team release Agents View, and that changed my mind for the good.
-
Running SDD Workflows with Local Copilot
This is article 5 of a series. Start with Mayday! We're Running Out of Fuel! for the manifesto, or How I Set Up GitHub Copilot CLI on Local Hardware for the setup story.
-
Copilot Instructions, Agents, and Skills: The Missing Control Layer
This is article 4 of a series. Start with Mayday! We're Running Out of Fuel! for the manifesto, or How I Set Up GitHub Copilot CLI on Local Hardware for the setup story.
-
MCP Is How Local Copilot Becomes Useful
This is article 3 of a series. Start with Mayday! We're Running Out of Fuel! for the manifesto, or How I Set Up GitHub Copilot CLI on Local Hardware for the setup story.
-
How I Set Up GitHub Copilot CLI on Local Hardware
Human words again. No polished corporate hallucination. Just my workstation, my setup, and what I learned wiring it together.
-
Local LLMs Under the Hood
Despite being an article about LLMs, this was written entirely by a human being. The only intelligence here today is yours. Enjoy!
-
Mayday! Mayday! We're Running Out of Fuel!
DISCLAIMER: these are my own words. Human words. No em dashes or "this is not X, but Y" sentences here and there. Just human intelligence and thoughts packed for your enjoyment. I just used ChatGPT to generate these funny images.