Technical Writing & Research

Deep dives into AI and LLM internals, cryptography, reverse engineering, and systems programming.

About

Languages

Frameworks

Databases & ORMs

Tooling & Infrastructure

Designed & Developed with by @ImKKingshuk

Back to Blog

Blog Categories

Browse posts by topic.

4 POSTS

AI

Model internals, long context, and how these systems actually behave.

Posts

>System One Models: How Non-Autoregressive Typed Decision Architectures Work >Inference-Efficient LLMs: How Sparse Compute and Compressed Memory Work >World Models: The Architecture Behind Spatial Intelligence >Multi-Million-Token Context LLMs: How Long Context and Large Parameter Models Work

Explore posts

2 POSTS

Security

Reverse engineering, mobile and network internals, and defending AI systems.

Posts

>LLM Security Shielding: Preventing Tool Injection in Model Context Protocol >Dismantling Android Keystore: Reversing Safe Storage & Key Attestation

Explore posts

1 POST

Systems

Low-level performance work, concurrency, and tooling in Rust and Python.

Posts

>Rust-Powered Recon: Building a Fast Network Engine

Explore posts

Technical Writing & Research

Deep dives into AI and LLM internals, cryptography, reverse engineering, and systems programming.

Back to Blog

Blog Categories

Browse posts by topic.

4 POSTS

AI

Model internals, long context, and how these systems actually behave.

Posts

Explore posts

2 POSTS

Security

Reverse engineering, mobile and network internals, and defending AI systems.

Posts

>LLM Security Shielding: Preventing Tool Injection in Model Context Protocol >Dismantling Android Keystore: Reversing Safe Storage & Key Attestation

Explore posts

1 POST

Systems

Low-level performance work, concurrency, and tooling in Rust and Python.

Posts

>Rust-Powered Recon: Building a Fast Network Engine

Explore posts