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