Writing

21 posts, oldest habits and newest obsessions.

2026

GPT Tokenizer(BPE Algo)Jul 2026

Inference (phases)Jul 2026

HR-Personal InterviewJul 2026

how llm’s pricing is decided (Reiner matx)Jul 2026

Language Modeling from Scratch Jul 2026

Codex Event 25th July (2026)Jul 2026

GpuJul 2026

keeping-up with AIJul 2026

Stanford CS336 | Language Modeling from ScratchJul 2026

2606.24937v1.pdfJul 2026

termsJul 2026

five practical problems for Agentic AI Architectures(make event)Jul 2026

Minimax-sparse-AttentionJun 2026

Understanding of dimension params in AttentionJun 2026

scaling llm modelsJun 2026

Calculating the no of parameters for modelsJun 2026

prompt vs context engineeringJun 2026

Being meJun 2026

RAGJun 2026

The anatomy of effective contextMar 2026

position iterpolation(extrapolation vs interpolation)Mar 2026