Edition of Saturday 14 November 2026

Adaptive Routing: Learning which model to trust

Comments on “Adaptive Routing: Learning which model to trust”

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

Sovereign, a model router described by its authors, learns which language model to trust for each kind of task from the outcomes of its own work, without labeled answers or prior knowledge of the models.

Read the original at sov.solibra.ai. 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. 110 of 123 with a score of 0.56. The panel rated it highest on new information (0.86) and reader interest (0.76), lowest on significance (0.58). The judges disagreed most on promotional (spread 0.52), so the story is marked contested. Placed No. 110, No. 107 by score alone: the 49th 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
Promotional product post for an AI model router with self-reported benchmarks, unverified grader claims, and single runs; the routing idea is relevant to AI builders but substantiation is weak.
AI judgeJudge 3gpt-5.6-luna
A technically detailed, benchmarked write-up of adaptive LLM routing with substantial cost and accuracy results. It is highly relevant and actionable, though self-reported experiments and broad production claims leave some promotional and overclaim risk.

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 0.52 on promotional

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.58
  • Reader interest0.76
  • Audience breadth0.67
  • Practical relevance0.74
  • Substantiated0.64
  • Technical depth0.65
  • New information0.86
  • Counts against: Promotional0.41
  • Counts against: Overclaim0.49

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?0.700.350.680.580.35+0.24+0.139
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.770.600.900.760.30+0.26+0.197
Audience breadthHow many people who build technology does it concern?0.800.500.700.670.30+0.13+0.087
Practical relevanceHow useful is it to someone who builds software or tech products?0.800.600.820.740.22+0.22+0.163
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.0.800.400.720.640.40+0.05+0.032
Technical depthHow technically substantive is it?0.750.450.760.650.31+0.05+0.033
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.850.800.940.860.14+0.05+0.043
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.0.180.700.350.410.52 , above the contested threshold−0.19−0.078
OverclaimDo the headline or conclusions claim more than the body supports?0.340.700.420.490.36−0.11−0.054
Sum of contributions+0.561
Claim-check penalty0.000
Total, as published0.561

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 #110 on Rubric, 14 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-14/110/"><img src="https://rubric.hrih.si/badge/2026-11-14/110.svg" alt="Ranked #110 on Rubric, 14 Nov 2026" width="252" height="28"></a>

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 15 Nov 2026, 20:44 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 “Adaptive Routing: Learning which model to trust”

More on Rubric

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