An LLM judge passed renders with defects I planted

No. 60 of 245 · Yaman Ahlawat · Yaman Ahlawat · published 23 Oct 2026, 16:50 UTC · 12 min read

Programming & dev tools
AI & machine learning
Write-up

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

A developer's follow-up to an earlier post on an LLM-driven Figma-to-React pipeline reports that the vision-model reviewer's scores vary by about 0.11 when the same render is scored repeatedly, so the 0.85 pass gate and many of the author's earlier comparisons were within noise.

Read the original at yamanahlawat.in. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Score

0.67total under rubric v2.0Contestedjudges differ by 0.43 on new information

Significance0.53
Reader interest0.75
Audience breadth0.46
Practical relevance0.78
Substantiated0.91
Technical depth0.93
New information0.81
Counts against: Promotional0.03
Counts against: Overclaim0.21

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	0.52	0.35	0.72	0.53	0.37	+0.25	+0.133
Reader interest	0.72	0.60	0.94	0.75	0.34	+0.20	+0.151
Audience breadth	0.45	0.30	0.62	0.46	0.32	+0.10	+0.046
Practical relevance	0.81	0.65	0.88	0.78	0.23	+0.15	+0.117
Substantiated	0.99	0.85	0.90	0.91	0.14	+0.10	+0.091
Technical depth	1.00	0.90	0.88	0.93	0.12	+0.10	+0.093
New information	0.91	0.55	0.98	0.81	0.43 , above the contested threshold	+0.10	+0.081
Promotional	0.04	0.05	0.01	0.03	0.04	−0.15	−0.005
Overclaim	0.34	0.20	0.08	0.21	0.26	−0.15	−0.031
Sum of contributions							+0.675
Claim-check penalty							0.000
Total, as published							0.675

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition and listed in its JSON. This one was scored under rubric v2.0; How ranking works describes the current rubric, v2.2.