# Journal 2026-02 > February 2026 journal journal ## Monthly retrospective Wrote a few pieces. Building new software keeps drawing my writing in this direction. - [Software assets in the AI era](https://wiki.g15e.com/en/pages/Software%20assets%20in%20the%20AI%20era.txt) - [Distorted user-centered design](https://wiki.g15e.com/en/pages/Distorted%20user-centered%20design.txt) - [Tasteful software](https://wiki.g15e.com/en/pages/Tasteful%20software.txt) (still refining it) In February, too, I did and closed my rings every single day. ## Journal ### 2026-02-28 Tidied up some notes I'd written around <2021>: [Distorted user-centered design](https://wiki.g15e.com/en/pages/Distorted%20user-centered%20design.txt). Thought about [software assets in the AI era](https://wiki.g15e.com/en/pages/Software%20assets%20in%20the%20AI%20era.txt). ### 2026-02-27 Added to the wiki. ### 2026-02-23 Finally started using two \$200 [Claude Code](https://wiki.g15e.com/en/pages/Claude%20Code.txt) accounts. I pay for one personally; the company supports the other. My monthly LLM subscription spending is now about \$1,200. ### 2026-02-18 Built a prototype collaboration system in which the user and AI agent each have an independent workspace, using virtualization. Again, something that would have taken a long time without [LLMs](https://wiki.g15e.com/en/pages/Large%20language%20model.txt) was done in two days. Having it embrace the "everything is a file" philosophy and make full use of Linux's existing capabilities produced a robust system without much code. ### 2026-02-17 Built a program to convert into [PDF](https://wiki.g15e.com/pages/Portable%20Document%20Format.txt), extracting TeX Live files so only the necessary ones download dynamically. Also implemented [Language Server Protocol](https://wiki.g15e.com/pages/Language%20Server%20Protocol.txt), with good support for renaming, go to definition, and so on. Without [LLMs](https://wiki.g15e.com/en/pages/Large%20language%20model.txt), I wouldn't even have considered starting, but it was all done in a day. ### 2026-02-11 Continuing to think about [tasteful software](https://wiki.g15e.com/en/pages/Tasteful%20software.txt), I wrote down a few more fragments of thoughts I've carried for a long time: - [Capabilities over features](https://wiki.g15e.com/en/pages/Capabilities%20over%20features.txt) - [Exceptional usability](https://wiki.g15e.com/en/pages/Exceptional%20usability.txt) ### 2026-02-09 Left the AI software dark factory running overnight and woke up to a code-delete-and-run (it deleted all the code and vanished). Just as a gambler who includes going all-in in their betting strategy is bound to lose everything eventually if they keep playing, without constraints this ending seems almost inevitable. Something like a is essential. ### 2026-02-06 With Opus 4.6 and Codex 5.3 (xhigh), even simple prompts increasingly lead to over 30 minutes of independent work. I like the results more, too. It feels as though a well-designed loop could keep them working all day without trouble. ### 2026-02-01 Created [AI and science](https://wiki.g15e.com/pages/AI%20and%20science.txt) and am collecting related news. --- Built a Chrome extension to help with [building skilled intuition for using LLMs](https://wiki.g15e.com/en/pages/Building%20skilled%20intuition%20for%20using%20LLMs.txt), but hardly use it. The easier making things becomes, the more important it seems to have the taste to decide what not to make. I should think even harder about [tasteful software](https://wiki.g15e.com/en/pages/Tasteful%20software.txt). --- Joined Corca.