Edition of Thursday 12 November 2026

AI proved your code correct. What did it actually prove?

Comments on “AI proved your code correct. What did it actually prove?”

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

Keller AI's engineering note explains how formal verification works and what it can actually establish about software. Using a sorting function as its example, it shows that a checked proof covers every input only under its stated specification and assumptions, while test runs only cover the cases tried.

Read the original at kellerai.io. 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. 78 of 106 with a score of 0.58. The panel rated it highest on reader interest (0.75) and technical depth (0.73), lowest on significance (0.57). Placed No. 78, No. 71 by score alone: the ninth Programming & dev tools story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Substantive essay on formal verification and AI-assisted proofs with worked examples, but mostly explanatory and partly promotional for the author's firm; its self-reported bank experiment is small and unreplicated.
AI judgeJudge 3gpt-5.6-luna
A technically substantive formal-verification explainer connects proofs, specifications, assumptions, security properties, and AI-assisted development. It offers useful caveats and a small unpublished experiment, but overlaps recent verification coverage and includes noticeable organizational promotion.

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 v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.57
  • Reader interest0.75
  • Audience breadth0.68
  • Practical relevance0.67
  • Substantiated0.58
  • Technical depth0.73
  • New information0.70
  • Counts against: Promotional0.29
  • Counts against: Overclaim0.28

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?0.640.400.680.570.28+0.24+0.138
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.810.600.830.750.23+0.26+0.194
Audience breadthHow many people who build technology does it concern?0.870.500.670.680.37+0.13+0.088
Practical relevanceHow useful is it to someone who builds software or tech products?0.720.550.720.670.17+0.22+0.146
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.0.630.400.720.580.32+0.05+0.029
Technical depthHow technically substantive is it?0.840.600.760.730.24+0.05+0.037
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.810.600.700.700.21+0.05+0.035
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.0.070.350.450.290.38−0.19−0.055
OverclaimDo the headline or conclusions claim more than the body supports?0.170.300.380.280.21−0.11−0.031
Sum of contributions+0.581
Claim-check penalty0.000
Total, as published0.581

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.

Ranked #78 on Rubric, 12 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-12/78/"><img src="https://rubric.hrih.si/badge/2026-11-12/78.svg" alt="Ranked #78 on Rubric, 12 Nov 2026" width="245" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 3 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 12 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 “AI proved your code correct. What did it actually prove?”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0