Edition of Saturday 21 November 2026

Keeping AI Coding Agent Memory Relevant as Code Changes

Comments on “Keeping AI Coding Agent Memory Relevant as Code Changes”

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

An experiment on Excalidraw and Vite examines how persistent knowledge saved by AI coding agents goes stale as code changes. Line-number references broke often: 56% of Excalidraw and 35% of Vite locations pointed to different functions at later revisions.

Read the original at enola.tech. 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. 114 of 118 with a score of 0.55. The panel rated it highest on new information (0.88) and technical depth (0.76), lowest on significance (0.48). The judges disagreed most on substantiated (spread 0.44), so the story is marked contested. Placed No. 114, No. 117 by score alone: the 45th 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 study of coding-agent memory staleness with measured data, but the piece is partly promotional for the [site] tool and the findings are modest in scope.
AI judgeJudge 3gpt-5.6-luna
A practical engineering study of source-aware memory for coding agents, with repository experiments, measured failure rates, CLI workflow, and important limitations. It is highly relevant and technically substantive, though scope and evaluation remain limited.

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 v2.3Contestedjudges differ by 0.44 on substantiated

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.48
  • Reader interest0.67
  • Audience breadth0.54
  • Practical relevance0.70
  • Substantiated0.73
  • Technical depth0.76
  • New information0.88
  • Counts against: Promotional0.27
  • Counts against: Overclaim0.26

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?0.580.300.560.480.28+0.24+0.116
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.680.500.840.670.34+0.26+0.175
Audience breadthHow many people who build technology does it concern?0.650.400.580.540.25+0.13+0.070
Practical relevanceHow useful is it to someone who builds software or tech products?0.810.550.730.700.26+0.22+0.153
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.0.940.500.740.730.44 , above the contested threshold+0.05+0.036
Technical depthHow technically substantive is it?0.920.600.770.760.32+0.05+0.038
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.860.850.930.880.08+0.05+0.044
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.0.100.500.220.270.40−0.19−0.052
OverclaimDo the headline or conclusions claim more than the body supports?0.190.400.180.260.22−0.11−0.028
Sum of contributions+0.553
Claim-check penalty0.000
Total, as published0.553

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 #114 on Rubric, 21 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-21/114/"><img src="https://rubric.hrih.si/badge/2026-11-21/114.svg" alt="Ranked #114 on Rubric, 21 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 2 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 21 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 “Keeping AI Coding Agent Memory Relevant as Code Changes”

More on Rubric

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