Huizi Mao

Over the past three months, every time I felt ready to write about coding agents and personal assistants, something new came out and my views needed updating.

LLM inference costs have dropped a lot over the past three years.

Quantization has been adopted by many model providers to reduce inference cost.

When people consider AI’s threats, unemployment tops the list.

I have always wondered how information analysis works in government intelligence agencies or corporate business intelligence departments.

Performance optimization of LLM systems requires a thorough understanding of the full software stack.

Disclaimer: This blog was originally published on OmniML’s website in November 2022.

You may have wondered how autograd actually works in imperative programming.