https://fujimon.com This is Yuya's blog RSS feed https://fujimon.com/blog/skills The default is model-invoked. For most of what we build, it should not be. Sat, 08 Aug 2026 00:00:00 GMT https://fujimon.com/blog/missing-ui The smartest AI agents fail without good UI for reviewing their output. That's why everything becomes a chat app. Tue, 02 Dec 2025 00:00:00 GMT https://fujimon.com/blog/llm-stack A deep dive into how modern AI applications mirror cloud infrastructure, breaking down each component from LLMs as compute engines to memory systems as databases, and exploring why a Heroku-like platform for LLMs could be transformative. Wed, 23 Jul 2025 00:00:00 GMT https://fujimon.com/blog/memory Models are good enough. The next unlock is memory: persistent, structured, and personalized rather than a bigger context window. Sun, 20 Jul 2025 00:00:00 GMT https://fujimon.com/blog/mirix A look at MIRIX, a modular memory architecture that helps AI assistants get past the "day one" problem Thu, 17 Jul 2025 00:00:00 GMT https://fujimon.com/blog/ai-memory The memory AI needs depends on what you are using it for. Tue, 08 Jul 2025 00:00:00 GMT https://fujimon.com/blog/linear-sync-engine My notes on Tuomas Artman's talk about Linear's sync engine: the object graph, the transaction queue, and how the read and write paths stay in sync. Wed, 14 Aug 2024 00:00:00 GMT https://fujimon.com/blog/why-im-excited-about-local-first-software Local-first software is a new approach to building applications that prioritize the user experience and data ownership. It's exciting because it simplifies the development process and makes applications more reliable. Sun, 28 Jul 2024 00:00:00 GMT https://fujimon.com/blog/crdt-for-mortals My note from "CRDTs for Mortals" by James Long at dotJS 2019 Fri, 08 Mar 2024 00:00:00 GMT https://fujimon.com/blog/optimism-inmemorycache How Apollo Client uses "optimism" to improve the performance of the cache Fri, 06 Sep 2019 00:00:00 GMT