Posts

All the articles I've posted.

• 
  llm-concepts

  23 Apr, 2026 · 7 min read

  Modern Alignment: RLHF, DPO, and Constitutional AI

  A base model just predicts tokens. Alignment turns it into an assistant that follows instructions and refuses harmful ones.

• 
  llm-concepts

  23 Apr, 2026 · 8 min read

  Mixture of Experts: Why 671B Does Not Equal 671B

  A 671B Mixture of Experts model can be faster and cheaper to run than a dense 70B. The headline parameter count stopped meaning what it used to mean.

• 
  llm-concepts

  23 Apr, 2026 · 6 min read

  Parameter Counts and Scaling Laws: What 70B Actually Means

  What does 70B actually mean? It tells you about memory requirements, inference speed, and training costs, but almost nothing about model quality on its own.

• 
  ai

  21 Apr, 2026 · 2 min read

  AI Digest W17: Models, Images, and the Agentic Bill Arrives

  Anthropic ships Opus 4.7 and Claude Design, OpenAI drops Images 2.0, Qwen3.6 opens up agentic coding, and GitHub sends the first real agentic compute invoice.

• 
  ai

  21 Apr, 2026 · 8 min read

  Context Windows: Why Your AI Has a Working Memory Limit

  Context windows are not memory. They are working memory. Here is what the model can see right now, why extending that limit is hard, and what it costs to try.

• 
  ai

  20 Apr, 2026 · 9 min read

  Positional Encoding and Sampling: How the Transformer Finds Position and Picks Its Next Word

  Attention cannot tell 'the dog bit the man' from 'the man bit the dog.' Positional encoding fixes that. Then sampling decides what word the model actually says.

• 
  ai

  20 Apr, 2026 · 7 min read

  Tokens and Embeddings: How Raw Text Becomes Numbers the Model Can Use

  Before the transformer can do anything, it must turn your prompt into numbers. Here is exactly how that works, from raw characters to dense vectors.

• 
  ai

  20 Apr, 2026 · 6 min read

  The Transformer: How Attention Solved the Problem Everything Else Could Not

  In 2017, eight researchers replaced the entire approach to language modeling with a single idea: let every word attend to every other word directly.

• 
  ai

  19 Apr, 2026 · 7 min read

  Before the Transformer: A Short History of Machines That Read

  Why did the transformer matter so much that we measure AI in 'before' and 'after' it? A short history of every approach that tried and hit a wall first.