Writing
Blog
Thoughts on software, infrastructure, and tools.
Another DeepSeek moment
Cheap and efficient models are changing the token economy. Is it still worth it to pay for more intelligent models, or is harness engineering the safer bet?
#ai#llm#economics#deepseek#qwen#harness-engineering
Part 1
Part 1: How to evaluate agents with grounded theory
A practical guide to using grounded theory to sample traces, identify failure modes, and turn qualitative judgment into scalable evaluation.