AI review optimized for recall (catches more defects than Codex or Claude)
Comments on “AI review optimized for recall (catches more defects than Codex or Claude)”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
QuickReview is a beta, self-hosted AI reviewer for GitHub pull requests that fans each change out to about a dozen narrow, read-only lens passes, merges duplicate findings, and has a validator re-check every candidate before posting one review.
Why it ranked
No. 155 of 155 with a score of 0.55. The panel rated it highest on new information (0.92) and technical depth (0.86), lowest on significance (0.51). Overclaim counted against it (0.51). The judges disagreed most on substantiated (spread 0.46), so the story is marked contested.
- AI judgeJudge 2claude-haiku-5-5
- Beta self-hosted AI code reviewer with heavily self-reported benchmarks, a mostly self-authored evaluation, and promotional framing; technically detailed and relevant to builders, but not landmark significance and claims exceed independent verification.
- AI judgeJudge 3gpt-5.6-luna
- A technically detailed launch of a self-hosted multi-agent code reviewer, with extensive benchmark data, reproducibility materials, architecture, safeguards, costs, and deployment guidance. Claims are unusually evidenced, though results are partly tuned and the piece promotes its own product.
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
0.55total under rubric v2.2Contestedjudges differ by 0.46 on substantiated
- Significance0.51
- Reader interest0.67
- Audience breadth0.52
- Practical relevance0.75
- Substantiated0.75
- Technical depth0.86
- New information0.92
- Counts against: Promotional0.25
- Counts against: Overclaim0.51
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 | 0.57 | 0.35 | 0.62 | 0.51 | 0.27 | +0.24 | +0.123 |
| Reader interest | 0.68 | 0.50 | 0.82 | 0.67 | 0.32 | +0.26 | +0.173 |
| Audience breadth | 0.60 | 0.40 | 0.55 | 0.52 | 0.20 | +0.13 | +0.067 |
| Practical relevance | 0.86 | 0.60 | 0.78 | 0.75 | 0.27 | +0.22 | +0.165 |
| Substantiated | 0.96 | 0.50 | 0.78 | 0.75 | 0.46 , above the contested threshold | +0.05 | +0.037 |
| Technical depth | 0.98 | 0.70 | 0.91 | 0.86 | 0.28 | +0.05 | +0.043 |
| New information | 0.94 | 0.85 | 0.97 | 0.92 | 0.12 | +0.05 | +0.046 |
| Promotional | 0.11 | 0.45 | 0.18 | 0.25 | 0.34 | −0.19 | −0.047 |
| Overclaim | 0.62 | 0.60 | 0.30 | 0.51 | 0.32 | −0.11 | −0.056 |
| Sum of contributions | +0.552 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.552 | ||||||
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/2026-10-28/155/"><img src="https://rubric.hrih.si/badge/2026-10-28/155.svg" alt="Ranked #155 on Rubric, 28 Oct 2026" width="252" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 5 pts, not on front page
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.