Hacker News: missmoss

For the First Time, AI Was My User

missmoss — Wed, 27 May 2026 13:44:31 +0000

Article URL: https://clairetsao.substack.com/p/for-the-first-time-ai-was-my-user

Comments URL: https://news.ycombinator.com/item?id=48294282

Points: 2

# Comments: 0

Mermaid Diagrams Are Unreadable in Real-World Technical Docs

missmoss — Mon, 18 May 2026 14:17:22 +0000

Article URL: https://clairetsao.substack.com/p/mermaid-diagrams-are-unreadable-in

Comments URL: https://news.ycombinator.com/item?id=48180265

Points: 2

# Comments: 0

New comment by missmoss in "Show HN: Verification of Human Understanding of LLM-Generated Work"

missmoss — Wed, 13 May 2026 16:29:36 +0000

Cool! I watched the demo. The concept makes sense. Quick thought: free-text answers might be high friction for adoption. Not sure if you'd consider various verification method, but something like multiple choice questions or "highlight the relevant code chunk" could be lower effort for the developer, and easier to evaluate programmatically too.

New comment by missmoss in "Ask HN: Do you need to look at the code?"

missmoss — Tue, 12 May 2026 16:06:00 +0000

When working on an existing project, I always take a close look on what got changed by LLM. Sometimes I explicitly tell it which line to change and nothing else. Like what most people found, LLM sometimes, if not always, creates redundant over-engineering work trying to be useful, while most of time it actually breaks something, e.g. code quality and readability. In new projects, I focus more on plan, spec, test scheme. I review how modules are set up and sometimes functions, but pay less attention on implementation details.

New comment by missmoss in "Show HN: Verification of Human Understanding of LLM-Generated Work"

missmoss — Tue, 12 May 2026 16:00:20 +0000

Curious if there's a demo/screenshot on what questions developers should expect and what acceptable answers look like. Checked out the repo but didn't find the showcase.