Vishal Bakshi's Blog

This is my first of a series of articles on one of the most fascinating concepts: the Normal distribution.

I’m dusting off my ColBERT maintenance hat and getting back into the rhythm of things.

ChatGPT’s illustration of the Cavern The Cavern represents the space of solutions.

In his book “The Power of PULL,” Rob Snyder articulates a sort of separation-of-concerns between customer/demand and business/supply.

It takes translation labor to collaborate well on a cross-functional team.

Snapshot of the book cover I recently came across a LinkedIn post sharing lessons from the book The Go-Giver (A Little Story about a Powerful Business Idea) by Bob Burg and John David Mann.

Background I recently published a blog post on how I’m excited to start my professional ML career after 8 years of being a data analyst, educator, fast.ai student and community member, and now stanford-futuredata/ColBERT maintainer.

Where I Am Today In 285 days, my current role as a data analyst will come to an end.

Background I’ve been redoing my colbert-ai index comparisons between PyTorch versions using bitsandbytes’ torch.allclose tolerances.

Background I recently learned that it’s best practice to use different torch.allclose tolerances based on the precision of the floating point value.

Background I’ve been redoing my colbert-ai index comparisons between PyTorch versions using bitsandbytes’ torch.allclose tolerances.

Background I’ve recently been documenting how PyTorch version changes impact stanford-futuredata/ColBERT (colbert-ai on PyPI) intermediate and final index artifacts.

Background In this notebook I’m going to explore how (and hopefully why) you can start with different codes.indices but end up with the same ivf and ivf_lengths when indexing a document collection using colbert-ai.

I recently surpassed my goal of publishing 50 machine learning blog posts in 2025.

Background In a previous blog post I showed how I traced index artifact differences between colbert-ai installs using torch==1.13.1 (the current pinned version) and torch==2.1.0 (the first version which produces different index artifacts) to a difference…

Background I’ll summarize the main points from the “Steering Semantic Data Processing with DocWrangler” paper by Shreya Shankar et al and share my commentary (something I’ve been doing more of lately).

I have recently found myself using the term “non-deterministic” to describe LLM behavior.

Background In a previous blog post I outlined two things: Which two subsequent PyTorch versions caused a divergence in stanford-futuredata/ColBERT index .pt artifacts (ConditionalQA document collection): Version A Version B All .pt Shapes Match?

Background I recently released colbert-ai==0.2.22 which removed the deprecated transformers.AdamW import among other changes.

Yesterday I learned of the Modal docs example showing how to start a jupyter server via a Modal tunnel.