Aug 1Abandoned the plan to automatically generate tags for search engines and removed the ad‑hoc tag display that was derived from filenames and categories K...Jul 30Felt extreme self‑doubt about progress after watching only data collection and chunk search for the past two months; ended up mostly watching AWS MLA Ud...Jul 28Purpose The previous record only stated that the actual Godot project was split into 134 chunks for searching and that related documents were included i...Jul 23Changed the domain root to a fixed page that reads the README introduction so that the latest‑date archive does not appear in search results like the si...Jul 21Using the Markdown → JSONL Converter, processed 1,422 of the 1,550 official‑document JSONL items. Continued execution of the Qwen Validation Debugger fr...Jul 18Using the Markdown → JSONL Converter, processed 1,383 of the 1,550 official‑document JSONL items. Configured the F‑strategy that connects BM25 + embeddi...Jul 17Using the Markdown → JSONL Converter, processed up to 1,328 official‑document JSONL items. Generated a favicon. Improved the SEO algorithm. Retrospectiv...Jul 15Worked on the bus heading to Seoul today. Reviewed classification, synthetic code generation, JSONL creation, and validation flow from the beginning bas...Jul 13Increased the amount of official documentation JSONL collected by the Markdown → JSONL Converter from 1,260 to 1,281 items. Continued logging in the Qwe...Jul 12Deployed the multilingual development diary app to production on Vercel. Deployment link: https://ideaworldlab.com Started with the Vercel default domai...Jul 10Proceeded with converting official documentation to JSONL using the Markdown → JSONL Converter, increasing the collection from 1,180 to 1,230 items. Fou...Jul 8Proceeded with the official documentation JSONL conversion using the Markdown → JSONL Converter, increasing the collection from 1,074 to 1,180 items Wor...