A code inspection of 'serious' LLM-generated code
Comments on “A code inspection of 'serious' LLM-generated code”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
A software engineer's lab note reports that a code inspection using the IfSQ Level 2 method rated LLM-generated code FF, a poor maintainability grade. The inspection found that LLMs can spot some problems humans miss, but the code they produce has serious defects that slowly erode the effectiveness of coding…
Why it ranked
No. 111 of 155 with a score of 0.57. The panel rated it highest on new information (0.79) and technical depth (0.78), lowest on significance (0.47).
- AI judgeJudge 2claude-haiku-5-5
- Detailed first-person experiment on LLM-generated code quality using IfSQ audit; substantive technical content on maintainability, though a single author's personal project, long and somewhat self-promotional in tone.
- AI judgeJudge 3gpt-5.6-luna
- A detailed practitioner account of auditing LLM-generated code, with concrete maintainability findings and remediation examples. Its evidence is largely one informal case study, and broad claims about LLM understanding exceed what the body establishes.
Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.
Score
0.57total under rubric v2.2
- Significance0.47
- Reader interest0.65
- Audience breadth0.64
- Practical relevance0.69
- Substantiated0.64
- Technical depth0.78
- New information0.79
- Counts against: Promotional0.05
- Counts against: Overclaim0.42
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| Significance | 0.49 | 0.35 | 0.58 | 0.47 | 0.23 | +0.24 | +0.114 |
| Reader interest | 0.58 | 0.60 | 0.78 | 0.65 | 0.20 | +0.26 | +0.170 |
| Audience breadth | 0.79 | 0.50 | 0.62 | 0.64 | 0.29 | +0.13 | +0.083 |
| Practical relevance | 0.75 | 0.60 | 0.72 | 0.69 | 0.15 | +0.22 | +0.152 |
| Substantiated | 0.80 | 0.55 | 0.57 | 0.64 | 0.25 | +0.05 | +0.032 |
| Technical depth | 0.97 | 0.70 | 0.68 | 0.78 | 0.29 | +0.05 | +0.039 |
| New information | 0.91 | 0.60 | 0.86 | 0.79 | 0.31 | +0.05 | +0.040 |
| Promotional | 0.07 | 0.05 | 0.02 | 0.05 | 0.05 | −0.19 | −0.009 |
| Overclaim | 0.33 | 0.30 | 0.62 | 0.42 | 0.32 | −0.11 | −0.046 |
| Sum of contributions | +0.574 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.574 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-10-28/111/"><img src="https://rubric.hrih.si/badge/2026-10-28/111.svg" alt="Ranked #111 on Rubric, 28 Oct 2026" width="252" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 3 pts, not on front page
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.