Context limits are a key factor when working with LLMs. Simply put - it's the number of tokens ("words" - roughly, sub-word pieces. https://tiktokenizer.vercel.app/ ) that a LLM can process, before …
Running LLMs Locally
There's a lot of regular news about new LLMs being released, with Gemma4 being the latest. A lot of people get stuck on the first step of how to run them locally - which is quite straightforward …
Fun with AI: Writing a program to calculate p95 to p99 latencies : Part 1
Table of Contents Purpose/Summary There are 2 purposes of this blog post: Target Audience The target audience is someone who's ideally working/worked on distributed systems already, …
Continue Reading about Fun with AI: Writing a program to calculate p95 to p99 latencies : Part 1 →
Fun with AI: Medical & Healthcare
I have a cousin who recently (2022) finished his MBBS studies, and is now doing his MD. I wanted to show him the power of Gen AI, how it can help him in his career, and how it's revolutionizing …
Exotel: Turning cold emails into opportunities
One of the things I love about business is how flexible things are, and how everything is just negotiation. Recently, I had the opportunity to turn a cold email (on my current Employer's email …
Continue Reading about Exotel: Turning cold emails into opportunities →
Marketing Strategy & Tactics: Whatsapp and Google Drive
Why does Facebook-owned WhatsApp only backup to Google Drive? What’s Google’s monetization plan with 15GB of storage for everyone? What’s the long-term gain? My parents' Google accounts storage was …
Continue Reading about Marketing Strategy & Tactics: Whatsapp and Google Drive →