Edition of Saturday 24 October 2026

Making Every Harness Durable

  • Programming & dev tools
  • AI & machine learning
  • Infrastructure & DevOps
  • Release

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

durable-harness is a new open-source package from Vercel that adds crash recovery to existing coding agent harnesses such as Pi, OpenCode, Codex, and Claude Code, without modifying them.

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

Score

0.62total under rubric v2.0

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 breadth0.56
  • Practical relevance0.80
  • Substantiated0.66
  • Technical depth0.85
  • New information0.91
  • Counts against: Promotional0.33
  • 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).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
Significance0.610.450.650.570.20+0.25+0.142
Reader interest0.720.700.820.750.12+0.20+0.149
Audience breadth0.590.550.550.560.04+0.10+0.056
Practical relevance0.920.700.780.800.22+0.15+0.120
Substantiated0.750.500.720.660.25+0.10+0.066
Technical depth0.940.800.820.850.14+0.10+0.085
New information0.910.850.960.910.11+0.10+0.091
Promotional0.130.450.420.330.32−0.15−0.050
Overclaim0.250.350.280.290.10−0.15−0.044
Sum of contributions+0.615
Claim-check penalty0.000
Total, as published0.616

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.