I’m a senior software engineer building production-grade generative AI integrations for O9 Solutions’ supply chain platform.
I write about the things that hold my attention, from engineering and GenAI to short stories and small day-to-day happenings.
I also run one of Bangalore’s longest running bookclubs, Broke Bibliophiles Bangalore.
If you’ve worked with LLMs for even a short while, by now you’re aware of a few things - LLMs are extremely powerful in generating text and fetching information about a vast variety of topics LLMs can perform computations and help you analyse data if armed with the right tools LLMs are not yet completely 100% reliable. This last point is where the building that you’re painstakingly constructing can crumble like a deck of cards very rapidly. And this is where LLM evaluations come in. ...
I work in the engineering division of a supply chain company and our development process, as most companies do, involves the setting up of our SaaS platform locally. This means that there are a lot of dependent services that need to be run first that support the overall execution of the platform. For e.g. - Our platform’s stack requires SQL Server, Solr, Redis, Postgres, RabbitMQ, MongoDB as core services to be running first. Once these are all running and available, a service called WebAPI can be run that makes use of some of the above to run as well. Following this, there are a few more microservices that need to run, but that need not be part of this article since the underlying concept will already come through with the above being demonstrated. ...
I’ve done some Napkin Math - an essential part of system design - in my different jobs in the last decade but it’s been ad-hoc or purpose driven at that moment and I’ve not thought about it much . Today, I came across a tweet from One2N and a rabbit hole of a blog by Simon Eskildsen after that and it made me want to consciously think about it for a few use cases if only to improve my engineering decisions. I’m sure I will get a lot of things wrong, but over time I hope to tune it to be right. ...
3 Blue 1 Brown is an amazing Youtube resource to learn Math and Physics concepts from! Manim is an opensource package created by them to help generate the animations they use to teach these concepts. In this article, I will create a similar video with the help of Claude and Manim! First, install miktex Then, in powershell, install ffmpeg : run choco install ffmpeg Create a new virtual environment and install manim and manimgl - uv pip install manim manimgl Use Claude to generate a manim program for a formula or something you want to demonstrate - E.g. : My Claude Example Create a program that you got out of claude - Manim Program for x-squared Execute it - manim -pql xsquared.py ExplainXSquared This results in this beautiful 3 Blue 1 Brown like video! - https://www.youtube.com/watch?v=5Ql_vAj0ZVs ...