Varun Srinivas

Hi, I'm Varun Srinivas.

I build for the joy of it: robots, astrology engines, music toys.

By day I'm the CTO and Chief AI Officer at Coditas, where I help enterprises run AI transformation initiatives to realize real ROI from AI.

Take a look at my projects, or find the code on GitHub.

Recent Logs

• 9 min read

Fine-Tuning a 0.6B Model to Run an Agent Entirely in Your Browser

I built a mini agent harness in JavaScript, fine-tuned Qwen3-0.6B on my RTX 3060 to be its brain, and ran the whole thing over WebGPU — no server, no API keys. The model went from 30% to 77.5% on a prior-auth review task. The GPU crashed four times during training and quantization turned out to be the real boss fight.

Read more →
• 9 min read

Fine-Tuning ≠ Knowledge Injection (I Built a Demo to Prove It)

I fine-tuned a real model on my RTX 3060 to settle an argument: fine-tuning teaches a model how to behave, not what to know. The model learned a perfect persona — and confidently invented every fact it was asked. Here's the experiment, the four broken adapters it took to get there, and the live demo.

Read more →