The AI was smarter than the person setting it up ...

After months of testing local LLMs, I found that productivity depends on tools, not just models.

Even an older workstation-class eGPU like the NVIDIA Quadro P2200 delivers dramatically faster local LLM inference than CPU-only systems, with token-generation rates up to 8x higher. Running LLMs ...

It’s now possible to run useful models from the safety and comfort of your own computer. Here’s how. MIT Technology Review’s How To series helps you get things done. Simon Willison has a plan for the ...

I was one of the first people to jump on the ChatGPT bandwagon. The convenience of having an all-knowing research assistant available at the tap of a button has its appeal, and for a long time, I didn ...