#slm

Five weeks, one free GPU, and a lesson about measuring before celebrating. One of my training runs...

How I get a confidence score for every option without generating text, and why that score should only...

There's a specific kind of frustration that comes from asking an AI model something in Bangla and...

One number that predicts most of your defects Selective laser melting (SLM), one flavor of...

Kalau ngomongin model bahasa sekarang, yang kebayang biasanya model dengan ukuran besar. Ratusan...

We've all been told the future of AI is in the cloud, with massive LLMs crunching data on remote...

One common mistake I see among people entering the AI field: They make an API call to an LLM, get a...

Your OpenClaw agent has direct access to your shell and your files, and it runs on a frontier model....

Ollama wasn't enough anymore In recent years, IDE extensions that talk directly to...

Yesterday I shared this post: "Building a small language model has never been this easy, introducing...

Small models don't run on devices— they run on a stack of quantization kernels, compilers, and accelerators that quietly change their behavior.

Small Language Models (SLMs) in 2026 are reshaping how companies deploy AI. While the media obsesses...