Daily Dose of Data Science

Daily Dose of Data Science

KV vs Prefix vs Prompt vs Semantic Caching
...explained with best practices in production.
 • Avi Chawla
[Hands-on] Turn Scientific Figures Into Structured Data with Mistral OCR
A full walkthrough of the extraction schema, with code.
 • Avi Chawla
Build a Multi-Agent GTM Intelligence System
...explained with code.
 • Avi Chawla
Preloading Knowledge Into a Model Instead of Retrieving It
How to process your corpus once, skip retrieval entirely, and serve every query from a stored cache. Three parts covering the full spectrum.
 • Avi Chawla
How Semantic Code Navigation Cuts Agent Token Costs by up to 36%
Understanding what an agent actually does with the tokens before it writes code.
 • Avi Chawla
What is (was?) GIL in Python?
...explained with code.
 • Avi Chawla
Kimi K3's Sandbox Problem Finally Has an Open-Source Fix
...explained with code.
 • Avi Chawla
Grok Bot Masterclass
Everything you need to understand, set up, and get real work out of Grok Bot.
 • Avi Chawla
How a GPU Actually Works
The intuition an LLM engineer needs. Understand techniques like quantization, speculative decoding, and continuous batching in one place.
 • Avi Chawla
A Cheaper Model Does Not Imply a Cheaper Turn
The practical implications of model routing, clearly explained.
 • Avi Chawla
How Production LLMs Reason Better At Inference Time
8 techniques, explained visually.
 • Avi Chawla
Continuous Batching in LLMs
The technique behind vLLM's 23x throughput jump and the default scheduler in every serving engine.
 • Avi Chawla
© 2026 Avi Chawla · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture