Dhaval Singh's Blog

Write

Some notes on Agentic search & Turbopuffer

Aug 31, 20256 min read490

Counting tokens at scale using tiktoken

Jul 22, 20252 min read739

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

We focus quite a bit on prompt caching @LittlebirdAI to ensure lower latencies and cost. But it's very tricky to get it right, esp when you deal with multiple providers. There are quite a few really g

Apr 22, 20262 min read

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

Jun 30, 20251 min read637

Resources to transition to 'Applied AI' role

Jun 27, 20253 min read244

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 read525

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 read223

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 read865

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 read192

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 read290

Command Palette

Latest articles