# beginning part (blogs) — RSS Amplifier Recent posts from the 2 feeds in the RSS Amplifier directory that cover beginning part. Page: Feed: --- ## [LLMs, from the Beginning — Part 1: The Next Token](https://ceres1.space/posts/llms-from-the-beginning/the-next-token/) _2026-08-06 · Posts on Coding in Space_ See how next-token completion becomes few-shot prompting, chat, tool use, and reasoning through interactive, token-level exhibits. ## [LLMs, from the Beginning — Part 2: Remembering the Prompt](https://ceres1.space/posts/llms-from-the-beginning/remembering-the-prompt/) _2026-08-06 · Posts on Coding in Space_ Open the KV cache, count what every remembered token costs, and explore how modern attention designs handle long context. ## [LLMs, from the Beginning — Part 3: Breaking the One-Token Barrier](https://ceres1.space/posts/llms-from-the-beginning/breaking-the-one-token-barrier/) _2026-08-06 · Posts on Coding in Space_ Connect arithmetic intensity, continuous batching, sparse experts, and speculative decoding to the latency each user feels. ## [Cipher – A Vision for the Future of Tab Completion](https://ceres1.space/posts/future-tab-completion/) _2025-02-14 · Posts on Coding in Space_ Tab-completion LLMs (large language models) are models that provide real-time suggestions while a developer types code, often integrated into editors ranging from Vim to IntelliJ as plugins, but sometimes as an integral part of the editor.