Top all-time · #18832
Hōrōshi バガボンド
Personal blog · blog.katanaquant.comprogrammingai
Hōrōshi バガボンド writes Vagabond Research, a personal blog at blog.katanaquant.com about programming and ai. Since 2026, 4 different Hacker News readers have linked it 4 times, most often “LLM Doesn't Write Correct Code. It Writes Plausible Code”. It is still writing: the last post was on 2026-04-03, and you can follow it by feed.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
Linked in comments about AI-generated code and rewrites, as a source for the point that LLM output needs a definition of correctness and measurement before it can be trusted. Used as supporting evidence, not praised directly.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
code monkey.
Most-linked posts?
- LLM Doesn't Write Correct Code. It Writes Plausible Code4 people · 4 mentions · first linked 2026-03-07
What Hacker News says?
Just a cautionary case of porting to Rust using AI https://blog.katanaquant.com/p/your-llm-doesnt-write-correct...
Comment linking /p/your-llm-doesnt-write-correct-code
on “Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc”Submitted LLM Doesn't Write Correct Code. It Writes Plausible Code as a story · 6 points
HN discussionAccording to the https://blog.katanaquant.com/p/your-llm-doesnt-write-correct... previously discussed on HN, it may be at least partially true: > The vibes are not enough. Define what correct means. Then measure.
Comment linking /p/your-llm-doesnt-write-correct-code
on “Claude built a system in 3 rounds, latent bugs from round 1 exploded in round 3”https://blog.katanaquant.com/p/your-llm-doesnt-write-correct... It can generate plausible code because the examples are already in the training set, the documentation, the how-to-write-a-database, other databases, etc. But unless you could write SQLite yourself it will be hard to specify a good one and to get the generator to produce a correct implementation.
Comment linking /p/your-llm-doesnt-write-correct-code
on “John Carmack about open source and anti-AI activists”