Article series
LLM Inside
The core ideas you need to make sense of an LLM, taken one at a time.
4 articles
The GS Certification Diary
Three weeks of reading 80 defect reports and rebuilding the code, the errors, and the manual
5 articles
The Harness Diary
Designing the execution environment an AI agent works in, from the ground up
10 articles
The Ontology Diary
Starting from the questions, building a knowledge graph, then working on quality and search
13 articlesAll articles
Tech NoteThe GS Certification Diary
Rebuilding error handling so failure says it failed (Part 3)
유지수
Tech NoteThe Harness Diary
The submit tool fired and the run kept going (Part 5)
김진수
Tech NoteThe Ontology Diary
Triple counts told us nothing about graph quality (Part 4)
김진수
Tech NoteThe GS Certification Diary
Replacing password hashing with argon2id on a live system (Part 2)
유지수
Tech NoteThe Harness Diary
The model that wrote the answer was also grading it (Part 4)
김진수