Kuala Lumpur, MY · est. 2023

Perivitta Rajendran

Your daily dose of complex AI concepts made simple, practical, and accessible for everyone.

61 posts writing since 2023
Recent writing

Recent writing

All posts →
Mixture of Experts (MoE): The Architecture Behind GPT-4, Mixtral, and Grok ai-engineering
Jun 6, 2026 47 mins read Advanced

Mixture of Experts (MoE): The Architecture Behind GPT-4, Mixtral, and Grok

Mixture of Experts (MoE): The Architecture Behind Frontier LLMs

Read post →
Diffusion Models Explained: The Math-Free Guide to How Stable Diffusion and DALL-E Work blogpost
Jun 5, 2026 34 mins read Beginner

Diffusion Models Explained: The Math-Free Guide to How Stable Diffusion and DALL-E Work

Diffusion Models Explained: The Math-Free Guide to How Stable Diffusion and DALL-E Work

Read post →
AI Agent Memory: Short-Term Context, Long-Term Storage, and Episodic Recall blogpost
Jun 4, 2026 29 mins read Intermediate

AI Agent Memory: Short-Term Context, Long-Term Storage, and Episodic Recall

AI Agent Memory: Short-Term Context, Long-Term Storage, and Episodic Recall

Read post →
AI assistant · powered by AI

Not sure where to start? Just ask.

Ask which post fits your problem, or anything about Peri's work on LLMs, RAG, and agents. It'll link you straight to the article.

From the archive

Browse all →