Topic: AI
All essays filed under "AI".
-
The Hidden Data Problem in Agentic AI Systems
AI systems do not just need data. They create data every time they run, and that changes how we design, debug, evaluate, and improve them.
-
Open Weights Is Not the Same as Open Source AI
A practical distinction between open-weight AI models and truly open source AI systems, and why the difference matters when choosing local LLMs.
-
What LLMs Do at Inference: A Deep Dive Under the Hood
Updated:A step-by-step, reference-backed explanation of what happens during LLM inference: tokenization, embeddings, prefill & decode phases, KV caching, decoding strategies, bottlenecks and optimizations like quantization, FlashAttention and speculative decoding.
-
Understanding Tokenizers in AI — A Deep Dive into ChatGPT, Grok, and Gemini
Updated:A complete guide to tokenizers in modern LLMs, covering BPE, WordPiece, SentencePiece, Unigram, and how ChatGPT, Grok, and Gemini tokenize text. Includes examples, real-world impact, and why tokenization is the foundation of AI.