Edition of Wednesday 18 November 2026

How the Claude Code team thinks about verification

Comments on “How the Claude Code team thinks about verification”

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

The Claude Code team at Anthropic describes its verification practices, saying roughly 90% of its code is written and reviewed by Claude. Its central claim is that cheap, agent-generated verification loops, such as end-to-end tests, property tests, and differential tests, let teams run many agents in parallel.

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

Why it ranked

No. 42 of 142 with a score of 0.66. The panel rated it highest on practical relevance (0.89) and reader interest (0.79), lowest on substantiated (0.54). The judges disagreed most on new information (spread 0.43), so the story is marked contested. Placed No. 42, No. 37 by score alone: the 14th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Practical engineering playbook on verifying AI coding agents' output; actionable and detailed, but largely a company process write-up with partly unsubstantiated claims and a promotional tone.
AI judgeJudge 3gpt-5.6-luna
A detailed engineering account of verification loops for AI-written code, with concrete test strategies, workflow controls, evaluation methods, and team practices. It is highly actionable, though some efficacy claims are internal and broad recommendations are partly opinionated.

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

0.66total under rubric v2.3Contestedjudges differ by 0.41 on significance, 0.43 on new information

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.60
  • Reader interest0.79
  • Audience breadth0.68
  • Practical relevance0.89
  • Substantiated0.54
  • Technical depth0.76
  • New information0.76
  • Counts against: Promotional0.21
  • Counts against: Overclaim0.36

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.700.350.760.600.41 , above the contested threshold+0.24+0.145
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.750.700.930.790.23+0.26+0.206
Audience breadthHow many people who build technology does it concern?0.690.600.740.680.14+0.13+0.088
Practical relevanceHow useful is it to someone who builds software or tech products?0.960.800.900.890.16+0.22+0.195
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.450.450.720.540.27+0.05+0.027
Technical depthHow technically substantive is it?0.860.700.720.760.16+0.05+0.038
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.850.500.930.760.43 , above the contested threshold+0.05+0.038
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.090.350.180.210.26−0.19−0.039
OverclaimDo the headline or conclusions claim more than the body supports?0.260.350.460.360.20−0.11−0.039
Sum of contributions+0.659
Claim-check penalty0.000
Total, as published0.659

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.

Ranked #42 on Rubric, 18 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-18/42/"><img src="https://rubric.hrih.si/badge/2026-11-18/42.svg" alt="Ranked #42 on Rubric, 18 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, front page

Discussion on Hacker News

Recorded for context only, checked 18 Nov 2026, 05:47 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. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “How the Claude Code team thinks about verification”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.