Dhaval Singh's Blog

Write

The cost of doing evals has gone down substantially...

May 19, 20264 min read66

K.I.S.S(Keep It Static, Stupid): System prompt ft. caching

Apr 22, 20265 min read329

Current Agentic Development Workflow(June)

How my development setup looks like using agents

Jun 3, 20262 min read208

Not All Caches Are Equal: Claude, OpenAI, and Gemini

Apr 22, 20262 min read118

Some notes on Agentic search & Turbopuffer

Aug 31, 20256 min read600

Counting tokens at scale using tiktoken

Using encode_to_numpy to count number of tokens in large strings to save memory and CPU

Jul 22, 20252 min read836

Run any LLM locally on your Mac in less than 2 mins

Yes, it's that simple

Jun 30, 20251 min read674

Resources to transition to 'Applied AI' role

I have seen quite a few software devs(including me) with little to no background in ML jumping on the genAI train in the last 1-2 years. While this is a good thing and using LLMs with no prior classical ML knowledge helps in some ways it is also a de...

Jun 27, 20253 min read258

Curated resources: AI Product x How to eval?

List of resouces for building a solid eval pipeline for your AI product

Mar 9, 20252 min read539

Order of fields in Structured output can hurt LLMs output

Evals on how does the order of fields in prompts w/ structured output(JSON) affect the LLM response quality

Jan 5, 20254 min read3.5K

Murphy's Law: Startup Version

10x Engineer or 0.1x

Oct 23, 20242 min read263

Command Palette

Latest articles