Edition of Saturday 21 November 2026

Google builds an artificial internet for its AI agents

Comments on “Google builds an artificial internet for its AI agents”

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

Google has built "Mirror Dimension," an isolated test environment with thousands of artificial websites, to expose its AI browser agents to prompt injection attacks without risking real-world actions.

Read the original at heise.de. 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. 117 of 118 with a score of 0.56. The panel rated it highest on reader interest (0.68) and technical depth (0.66), lowest on new information (0.47). The judges disagreed most on new information (spread 0.62), so the story is marked contested. Placed No. 117, No. 101 by score alone: the 48th AI & machine learning story of the day (−0.080), and close to “Mirror Dimension for Agents: Evaluating Browser-Use Agents Without the Web”, No. 15 on Friday 20 November 2026 (−0.026). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Covers Google's isolated synthetic-web test environment for prompt-injection testing of browser agents. Relevant to AI and security builders, with a sketch of method but limited independent evidence and no primary source.
AI judgeJudge 3gpt-5.6-luna
A technically credible report on an isolated artificial web for testing browser-agent prompt-injection resistance, with useful implementation details. Its novelty is low because the provided recent-story list already includes Mirror Dimension.

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

0.56total under rubric v2.3Contestedjudges differ by 0.62 on new information

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.56
  • Reader interest0.68
  • Audience breadth0.58
  • Practical relevance0.60
  • Substantiated0.51
  • Technical depth0.66
  • New information0.47
  • Counts against: Promotional0.10
  • Counts against: Overclaim0.20

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?0.610.400.680.560.28+0.24+0.135
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.650.600.800.680.20+0.26+0.178
Audience breadthHow many people who build technology does it concern?0.520.500.720.580.22+0.13+0.075
Practical relevanceHow useful is it to someone who builds software or tech products?0.610.500.700.600.20+0.22+0.133
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.0.460.450.620.510.17+0.05+0.025
Technical depthHow technically substantive is it?0.740.550.680.660.19+0.05+0.033
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.620.700.080.470.62 , above the contested threshold+0.05+0.023
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.0.120.100.080.100.04−0.19−0.019
OverclaimDo the headline or conclusions claim more than the body supports?0.220.250.120.200.13−0.11−0.022
Sum of contributions+0.562
Claim-check penalty0.000
Total, as published0.562

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 #117 on Rubric, 21 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-21/117/"><img src="https://rubric.hrih.si/badge/2026-11-21/117.svg" alt="Ranked #117 on Rubric, 21 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN —

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 “Google builds an artificial internet for its AI agents”

More on Rubric

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