Edition of Sunday 15 November 2026

TriusLD – A Small Tokenizer for LLMs with Robust Multilingual Support

Comments on “TriusLD – A Small Tokenizer for LLMs with Robust Multilingual Support”

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

TriusLD is a 65,535-slot tokenizer for LLMs that allocates vocabulary across 19 writing systems using per-script quotas plus a shared byte fallback. Its author reports 0.52 tokens per character averaged over 58 languages, versus 0.84 for GPT-4's vocabulary, while English gets 3.85 characters per token, about 18% behind a 200,000-token…

Read the original at trius.canton.graphics. 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. 50 of 62 with a score of 0.58. The panel rated it highest on technical depth (0.93) and new information (0.91), lowest on significance (0.48). The judges disagreed most on reader interest (spread 0.45), so the story is marked contested. Placed No. 50, No. 47 by score alone: the 25th 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
Detailed, technically specific tokenizer writeup with measured results and honest tradeoffs, but a narrow niche audience and a self-published, lightly validated project with a few overclaims.
AI judgeJudge 3gpt-5.6-luna
Detailed, reproducible tokenizer design and multilingual benchmark results offer actionable insight for model builders. Evidence is substantial but largely self-reported, with in-domain evaluation and some ambitious comparisons limiting significance and confidence.

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 v2.3Contestedjudges differ by 0.45 on reader interest

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.48
  • Reader interest0.66
  • Audience breadth0.57
  • Practical relevance0.64
  • Substantiated0.79
  • Technical depth0.93
  • New information0.91
  • Counts against: Promotional0.12
  • 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?0.530.300.620.480.32+0.24+0.116
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.630.450.900.660.45 , above the contested threshold+0.26+0.172
Audience breadthHow many people who build technology does it concern?0.590.400.720.570.32+0.13+0.074
Practical relevanceHow useful is it to someone who builds software or tech products?0.650.500.780.640.28+0.22+0.141
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.0.980.600.780.790.38+0.05+0.039
Technical depthHow technically substantive is it?1.000.850.930.930.15+0.05+0.046
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.920.850.970.910.12+0.05+0.046
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.0.070.200.080.120.13−0.19−0.022
OverclaimDo the headline or conclusions claim more than the body supports?0.260.350.180.260.17−0.11−0.029
Sum of contributions+0.583
Claim-check penalty0.000
Total, as published0.583

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 #50 on Rubric, 15 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-15/50/"><img src="https://rubric.hrih.si/badge/2026-11-15/50.svg" alt="Ranked #50 on Rubric, 15 Nov 2026" width="245" 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, 20:46 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 “TriusLD – A Small Tokenizer for LLMs with Robust Multilingual Support”

More on Rubric

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