Archive
The cost of doing evals has gone down substantially...
K.I.S.S(Keep It Static, Stupid): System prompt ft. caching
Not All Caches Are Equal: Claude, OpenAI, and Gemini
Some notes on Agentic search & Turbopuffer
Counting tokens at scale using tiktoken
Run any LLM locally on your Mac in less than 2 mins
Resources to transition to 'Applied AI' role
Curated resources: AI Product x How to eval?
Order of fields in Structured output can hurt LLMs output
Murphy's Law: Startup Version
Experiments with gpt-4o vision and architecture diagrams
Notes on evals in LLM-based applications
Looping defaultdict In Templates: A long-standing "Bug" in Django
Tech Tradeoffs #1: Django or Rails? MySQL or MongoDB?
A Gentle Introduction to AI Chat Bot Concepts
How Truly Random are Random Numbers?
Talk: Andaz Apna Apna
To raise or not to raise?
What the pluck?
Talk: Ruby's GVL Under The Microscope
Understanding Rails Callbacks & Common Pitfalls
Debugging Adventures #2: Memory Leaks In Database
Debugging Adventures #1: Memory and Sidekiq
How Ruby internals work