Two data streams for a happy website. Useful architectural concept for scaling: keep user-specific and generic data separate from the start, in recognition of their different caching and partitioning constraints.
Recent articles
- How often do LLMs snitch? Recreating Theo's SnitchBench with LLM - 31st May 2025
- Talking AI and jobs with Natasha Zouves for News Nation - 30th May 2025
- Large Language Models can run tools in your terminal with LLM 0.26 - 27th May 2025