Learn Something

How Production AI Systems Actually Work.

AI infrastructure discussions are increasingly about inference throughput, not training FLOPs.

People who learn fastest aren't chasing answers. They're reducing blind spots.

How SGLang Optimizes LLM Serving.

The world rarely rewards what is difficult. It rewards what is useful.

The value of time is measured by what remains after it passes.

Guide to AI precision formats.

The evolution of software.

Continuous batching keeps GPUs busy and LLMs fast.

Something nobody could've imagined 2-3 years back. All ten of the top open-weight models come from China-based labs.

The utilities have two bidders now. Defensive money and datacenter power money are buying the same sector for opposite reasons.

Guide to scalable LLM serving architecture.

The biggest cost isn't making mistakes. It's repeating the same ones without learning.

The deepest understanding comes from seeing how separate ideas influence one another.

The internet gave AI a lot of knowledge. Interactive environments are where it starts gaining experience.

AI models aren't competing on quality alone anymore. Cost per inference and ROI matter just as much.