Dhaval Singh's Blog

Write

Counting tokens at scale using tiktoken

Jul 22, 20252 min read729

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

Jun 30, 20251 min read616

Some notes on Agentic search & Turbopuffer

Practical pointers for doing Agentic, Hybrid search & Turbopuffer quirks

Aug 31, 20256 min read477

Resources to transition to 'Applied AI' role

Jun 27, 20253 min read226

Curated resources: AI Product x How to eval?

Mar 9, 20252 min read523

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 read3.3K

Murphy's Law: Startup Version

10x Engineer or 0.1x

Oct 23, 20242 min read220

Experiments with gpt-4o vision and architecture diagrams

Eval based experimentation to figure out how well it works with architecture diagrams

Oct 22, 20244 min read859

Notes on evals in LLM-based applications

A big lesson I've learned while building LLM-based applications: "Unless you have a closed feedback loop, nothing you do will be good enough" Allow me to explain. When building an LLM app, I constantly found myself chasing 100s of different optimizat...

Jul 22, 20242 min read191

Looping defaultdict In Templates: A long-standing "Bug" in Django

I am new to Django and recently spent a good chunk of time trying to debug what I thought was quite trivial. Looping a defaultdict in templates. This is a pretty common pattern when using Django, using a dict to pass and render data via templates, bu...

May 12, 20243 min read288

Tech Tradeoffs #1: Django or Rails? MySQL or MongoDB?

How did we decide which framework and database to use while building Seezo

Mar 17, 20244 min read559

Command Palette

Latest articles