Subscribe
Sign in
Home
Notes
Archive
About
The Illusion of Illusion... of AI?
A Builder's front row seat to the AI Reasoning Wars and what the Apple vs. Anthropic debate really means for those of us who build.
Jul 7
•
Shivani Virdi
22
June 2025
An Engineer's Guide to Fine-Tuning LLMs, Part 2: The Execution Playbook
A deep dive into the methods, fine-tuning pipeline, and operational risks of building specialised models.
Jun 21
•
Shivani Virdi
57
2
An Engineer’s Guide to Fine-Tuning LLMs – Part 1
Understand where fine-tuning fits in the LLM lifecycle, how it compares to prompting or retrieval — and when it’s the right tool for the job.
Jun 12
•
Shivani Virdi
46
2
May 2025
The Dangerous Thing About AI Hype?
Before the Next Deep Dive, A Message for the Builders.
May 23
•
Shivani Virdi
15
Inside DeepSeek-R1: A Masterclass in Incentivising Intelligence
What DeepSeek-R1 really teaches us: how to build models that learn, align, and evolve — without millions of labels.
May 15
•
Shivani Virdi
13
The Engineer’s Guide to RAG
Make Your Dumb Model Useful: A Dead-Simple Guide to Retrieval-Augmented Generation
May 7
•
Shivani Virdi
75
1
April 2025
Why Every AI Builder Needs to Understand MCP
The Model Context Protocol is redefining how we build with AI. Here’s what it is, why it matters, and how to use it to build your own modular AI Second…
Apr 30
•
Shivani Virdi
54
6
How GPTs Learn to Be Helpful
The missing step between raw model and assistant—and why it matters for builders
Apr 23
•
Shivani Virdi
25
9
How GPTs Are Born: Internet Feeding, Token by Token
Inside the system that turned web text into compressed intelligence—how GPTs learn, predict, and sometimes hallucinate.
Apr 16
•
Shivani Virdi
54
10
Welcome to NeoSage
Where you dive deep into the what, why and how of AI. No fluff. No hype. Your weekly window into applied AI engineering.
Apr 6
•
Shivani Virdi
23
7
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
