Edition of Friday 13 November 2026

Kiln – A WebGPU alternative to transformers.js, 2.2× faster (median)

Comments on “Kiln – A WebGPU alternative to transformers.js, 2.2× faster (median)”

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

Kiln is an MIT-licensed JavaScript library, published by Erdem Ozkan on GitHub, that runs language, vision and speech models in the browser on WebGPU directly from their original safetensors, pytorch or GGUF files, with no ONNX export or server.

Read the original at github.com. 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. 119 of 137 with a score of 0.57. The panel rated it highest on new information (0.92) and practical relevance (0.77), lowest on audience breadth (0.47). Placed No. 119, No. 118 by score alone: the 42nd 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
A new open-source WebGPU library for running original model weights in browsers, with a benchmark claim of 2.2x median speedup vs transformers.js; well-documented and checked for correctness, but early-stage and niche in audience.
AI judgeJudge 3gpt-5.6-luna
A substantive launch of a browser-native WebGPU inference library, with API examples, architecture details, compatibility notes, and comparative benchmarks. It is highly actionable for web and AI developers, though significance is limited by early-stage scope and model coverage.

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

0.57total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.47
  • Reader interest0.71
  • Audience breadth0.47
  • Practical relevance0.77
  • Substantiated0.74
  • Technical depth0.68
  • New information0.92
  • Counts against: Promotional0.22
  • Counts against: Overclaim0.28

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?0.560.300.550.470.26+0.24+0.113
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.700.600.820.710.22+0.26+0.184
Audience breadthHow many people who build technology does it concern?0.520.400.480.470.12+0.13+0.061
Practical relevanceHow useful is it to someone who builds software or tech products?0.840.700.780.770.14+0.22+0.170
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.0.880.550.780.740.33+0.05+0.037
Technical depthHow technically substantive is it?0.760.600.680.680.16+0.05+0.034
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.890.900.980.920.09+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.0.140.350.180.220.21−0.19−0.042
OverclaimDo the headline or conclusions claim more than the body supports?0.320.400.120.280.28−0.11−0.031
Sum of contributions+0.571
Claim-check penalty0.000
Total, as published0.571

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 #119 on Rubric, 13 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-13/119/"><img src="https://rubric.hrih.si/badge/2026-11-13/119.svg" alt="Ranked #119 on Rubric, 13 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 5 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 15 Nov 2026, 20:42 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 “Kiln – A WebGPU alternative to transformers.js, 2.2× faster (median)”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0