Swapan Rajdev
Subscribe
Sign in
Home
Archive
About
A Summary of LLM Post-Training Techniques
Why fine-tuning, reinforcement learning, and test-time scaling are essential to turning language models into useful agents.
Mar 27
•
Swapan
2
Share this post
Swapan Rajdev
A Summary of LLM Post-Training Techniques
Copy link
Facebook
Email
Notes
More
Building Moats in the Age of AI
Strategies for Sustainable Competitive Advantage
Mar 19
•
Swapan
5
Share this post
Swapan Rajdev
Building Moats in the Age of AI
Copy link
Facebook
Email
Notes
More
2
February 2025
The AI Stack: Understanding the Key Layers Powering the AI Ecosystem
A Breakdown of AI Infrastructure, Data, Models, Tooling, and Applications for Builders and Businesses
Feb 26
•
Swapan
2
Share this post
Swapan Rajdev
The AI Stack: Understanding the Key Layers Powering the AI Ecosystem
Copy link
Facebook
Email
Notes
More
January 2025
Understanding GPU Components for LLMs
In the fast-evolving world of artificial intelligence, each new GPU release is met with a mix of excitement and scrutiny.
Jan 8
•
Swapan
Share this post
Swapan Rajdev
Understanding GPU Components for LLMs
Copy link
Facebook
Email
Notes
More
DeepSeek-V3: The Pinnacle of Open-Source AI
DeepSeek-V3 currently stands as the best open-source AI model, decisively outperforming competitors such as Llama 3.1 405B, Qwen, and Mistral in…
Jan 3
•
Swapan
Share this post
Swapan Rajdev
DeepSeek-V3: The Pinnacle of Open-Source AI
Copy link
Facebook
Email
Notes
More
November 2024
Understanding Agentic AI Architecture
A Comprehensive Guide for Beginners to Experts
Nov 26, 2024
•
Swapan
1
Share this post
Swapan Rajdev
Understanding Agentic AI Architecture
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts