Here Be Monsters: What Do You Still Need to Know When Agents Do the Work?
Comments on “Here Be Monsters: What Do You Still Need to Know When Agents Do the Work?”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
An engineer describes a CI failure in a codebase built largely by a coding agent: SonarQube flagged App.tsx for cyclomatic complexity, and the agent had written components on single lines.
Why it ranked
No. 104 of 155 with a score of 0.58. The panel rated it highest on audience breadth (0.82) and reader interest (0.71), lowest on substantiated (0.27). The judges disagreed most on new information (spread 0.66), so the story is marked contested.
- AI judgeJudge 2claude-haiku-5-5
- Opinion essay on how agentic coding changes system ownership and training engineers. Relevant to builders and widely discussed topic, but unsubstantiated, no new information in the news set, and mostly an analogy-driven argument with a personal anecdote.
- AI judgeJudge 3gpt-5.6-luna
- A thoughtful, relevant argument about software ownership and engineering education in an agent-mediated development era, grounded mainly in anecdotes and analogies rather than systematic evidence or reproducible technical detail.
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
0.58total under rubric v2.2Contestedjudges differ by 0.66 on new information
- Significance0.53
- Reader interest0.71
- Audience breadth0.82
- Practical relevance0.63
- Substantiated0.27
- Technical depth0.45
- New information0.59
- Counts against: Promotional0.05
- Counts against: Overclaim0.29
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 | 0.68 | 0.30 | 0.62 | 0.53 | 0.38 | +0.24 | +0.128 |
| Reader interest | 0.70 | 0.60 | 0.82 | 0.71 | 0.22 | +0.26 | +0.184 |
| Audience breadth | 0.97 | 0.72 | 0.76 | 0.82 | 0.25 | +0.13 | +0.106 |
| Practical relevance | 0.72 | 0.50 | 0.68 | 0.63 | 0.22 | +0.22 | +0.139 |
| Substantiated | 0.17 | 0.25 | 0.38 | 0.27 | 0.21 | +0.05 | +0.013 |
| Technical depth | 0.58 | 0.30 | 0.48 | 0.45 | 0.28 | +0.05 | +0.023 |
| New information | 0.86 | 0.20 | 0.72 | 0.59 | 0.66 , above the contested threshold | +0.05 | +0.030 |
| Promotional | 0.07 | 0.05 | 0.03 | 0.05 | 0.04 | −0.19 | −0.010 |
| Overclaim | 0.29 | 0.30 | 0.28 | 0.29 | 0.02 | −0.11 | −0.032 |
| Sum of contributions | +0.581 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.581 | ||||||
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/2026-10-28/104/"><img src="https://rubric.hrih.si/badge/2026-10-28/104.svg" alt="Ranked #104 on Rubric, 28 Oct 2026" width="252" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 166 pts, front page
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.