idea_world_labDEV JOURNAL
Wednesday, July 8, 2026

July 8, 2026

  • Progressed the official document JSONL conversion count with the Markdown → JSONL Converter from 1,074 to 1,180
  • Worked with an SSAFY peer early in the morning, discussing AI philosophy, astronomy, and various hypotheses, which felt like my thinking broadened considerably
  • Talked with the SSAFY peer on the topic “Would AI be the same as humans?” and considered AI learning alongside human learning
    • The process of a baby learning the world through senses such as sight, hearing, and smell seemed like SFT, and the way parents correct repeated utterances could be seen as DPO
    • Imagined that if we built an AI simulation, we could include a childhood AI, a trained AI, and descendant/extinction/birth events, as well as natural events like Earth formation, evolution, meteor impacts, and earthquakes
    • If all AIs shared the same philosophy and safety rules, they might converge to an average or collapse, so an ecosystem of AIs with different philosophies and capabilities may be needed
    • Age‑related memory decline or dementia can be likened to AI hallucinations, and journaling/reading/context grasp feels like ongoing learning and memory correction for humans as well
  • Briefly checked the reference material shared by the SSAFY peer
    • Docusaurus Playground: a page for trying out the Docusaurus documentation site directly in the browser
    • DesignCompass’s Meta Astryx article: an article about Meta’s publicly released React + StyleX‑based design system. It was interesting that the design system was crafted to be understandable and usable by AI coding agents
  • Noted that as the README grows, Qwen PR Review may miss the actual code‑review context because it spends time reading the README body
  • Modified the Qwen PR Review workflow to exclude README.md from the review input
  • Recorded entries 23 through 32 with the Qwen Validation Debugger
  • Retrospective: docs/retrospectives/2026-07-08.md