Palette: teaching a small model to build decks in your design language
Comments on “Palette: teaching a small model to build decks in your design language”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
Palette is a self-hostable approach that fine-tunes a 20B open-weight model with LoRA to generate slide decks in the IBM Design Language, splitting work between a designer role that writes a JSON brief and a coder role that draws each slide in parallel.
Why it ranked
No. 101 of 137 with a score of 0.58. The panel rated it highest on new information (0.92) and technical depth (0.80), lowest on audience breadth (0.50). The judges disagreed most on significance (spread 0.42), so the story is marked contested. Placed No. 101, No. 97 by score alone: the 43rd 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 engineering writeup of fine-tuning a small open model for slide generation with a harness, relevant to AI builders, with benchmark results but mostly self-reported evaluation and a somewhat promotional tone.
- AI judgeJudge 3gpt-5.6-luna
- A technically detailed write-up on fine-tuning, synthetic data, structured generation, rendering validation, and repair for open-weight deck generation. It offers reproducible ideas and benchmark evidence, though some claims rely on reported results rather than fully inspectable artifacts.
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 0.42 on significance
- Significance0.52
- Reader interest0.72
- Audience breadth0.50
- Practical relevance0.67
- Substantiated0.71
- Technical depth0.80
- New information0.92
- Counts against: Promotional0.15
- Counts against: Overclaim0.33
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.55 | 0.30 | 0.72 | 0.52 | 0.42 , above the contested threshold | +0.24 | +0.125 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.72 | 0.55 | 0.90 | 0.72 | 0.35 | +0.26 | +0.188 |
| Audience breadthHow many people who build technology does it concern? | 0.56 | 0.35 | 0.58 | 0.50 | 0.23 | +0.13 | +0.065 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.77 | 0.45 | 0.78 | 0.67 | 0.33 | +0.22 | +0.146 |
| 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. | 0.80 | 0.60 | 0.72 | 0.71 | 0.20 | +0.05 | +0.035 |
| Technical depthHow technically substantive is it? | 0.86 | 0.70 | 0.82 | 0.80 | 0.17 | +0.05 | +0.040 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.89 | 0.90 | 0.98 | 0.92 | 0.09 | +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. | 0.09 | 0.25 | 0.12 | 0.15 | 0.16 | −0.19 | −0.029 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.45 | 0.35 | 0.20 | 0.33 | 0.25 | −0.11 | −0.037 |
| Sum of contributions | +0.580 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.580 | ||||||
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.
<a href="https://rubric.hrih.si/editions/2026-11-04/101/"><img src="https://rubric.hrih.si/badge/2026-11-04/101.svg" alt="Ranked #101 on Rubric, 4 Nov 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN —
Recorded for context only, checked 4 Nov 2026, 05:47 UTC. It played no part in the ranking.