Posts tagged "explainers"

Open original

This is an index page listing every post Sean Goedecke has tagged "explainers," covering topics like LLMs, DeepSeek, Model Context Protocol, blockchain, diffusion models, and interpretability. It's a jumping-off point rather than an article with a single argument.

  • The index is dominated by AI topics: how LLMs and ChatGPT work, DeepSeek's cost and reasoning work, MCP, and interpretability.
  • Blockchain shows up several times, including a Stripe "Tempo" FAQ and beginner-level primers.
  • A few posts fall outside AI and blockchain, such as how to read code, code review mistakes, and writing technical explanations.

This page is a tag index from Sean Goedecke's blog, not a single article, and it lists nineteen posts tagged "explainers." The titles cluster into a few clear groups. The biggest is AI and LLMs: how LLMs work, how ChatGPT works, diffusion models explained simply, Building LLM-driven agents, Model Context Protocol explained as simply as possible, How to actually use Model Context Protocol, and Porting and hacking Llama2.c for fun and profit. Two posts focus on DeepSeek, one asking what DeepSeek figured out about reasoning with DeepSeek-R1 and another on why DeepSeek is cheap at scale but expensive to run locally. There are also two interpretability pieces, one arguing that AI interpretability is further along than expected and another comparing its problems to those of philosophy of mind. The rest of the list is a mix. There are two blockchain primers (Blockchain explained simply and Blockchain for beginners), an unofficial FAQ on Stripe's Tempo blockchain, and a post on MCTS and LLMs that asks what the fuss is about. Outside AI and crypto, the entries include How to read code, Mistakes I see engineers making in their code reviews, Writing good technical explanations, and an older tutorial on building multiplayer games with socket.io and HTML5 Canvas. From the titles alone, the most useful reads for someone wanting to get oriented are probably "How LLMs work" and "Model Context Protocol explained as simply as possible," since they target the topics with the most ongoing confusion. The DeepSeek-R1 reasoning post and the local-versus-scale cost post are good picks if you already know the basics. The code review and technical writing posts are the practical ones for working engineers. To know whether any of these hold up, you'd need to open the individual posts, since this index only gives titles and not the content itself.

Ask about this article