From 22 GB to 5.3 GB: all of Hacker News, searchable offline
Comments on “From 22 GB to 5.3 GB: all of Hacker News, searchable offline”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
An open-source project compresses all 49.3 million Hacker News items from 2006 to 2026 into a 5.34 GB file searchable offline on a laptop CPU. It embeds each item once using EmbeddingGemma 2 on an integrated GPU, stores 256-bit binary codes, and reranks candidates at query time.
Why it ranked
No. 105 of 127 with a score of 0.57. The panel rated it highest on new information (0.84) and technical depth (0.74), lowest on significance (0.44). The judges disagreed most on substantiated (spread 0.43), so the story is marked contested. Placed No. 105, No. 102 by score alone: the 47th 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
- Open-source side project with a substantive technical write-up on binary embeddings and offline search; benchmarks are self-reported and narrow, so significance and substantiation are moderate.
- AI judgeJudge 3gpt-5.6-luna
- A technically specific open-source side project with reproducible implementation details, compression and retrieval metrics, and practical offline search. It is useful to developers, though significance is limited by niche scope and modestly reported evaluation.
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 v2.3Contestedjudges differ by 0.43 on substantiated
- Significance0.44
- Reader interest0.71
- Audience breadth0.50
- Practical relevance0.67
- Substantiated0.72
- Technical depth0.74
- New information0.84
- Counts against: Promotional0.12
- Counts against: Overclaim0.24
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? | 0.46 | 0.35 | 0.50 | 0.44 | 0.15 | +0.24 | +0.105 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.68 | 0.60 | 0.86 | 0.71 | 0.26 | +0.26 | +0.185 |
| Audience breadthHow many people who build technology does it concern? | 0.66 | 0.40 | 0.45 | 0.50 | 0.26 | +0.13 | +0.066 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.69 | 0.55 | 0.78 | 0.67 | 0.23 | +0.22 | +0.148 |
| 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. | 0.93 | 0.50 | 0.72 | 0.72 | 0.43 , above the contested threshold | +0.05 | +0.036 |
| Technical depthHow technically substantive is it? | 0.82 | 0.70 | 0.70 | 0.74 | 0.12 | +0.05 | +0.037 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.85 | 0.70 | 0.97 | 0.84 | 0.27 | +0.05 | +0.042 |
| 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. | 0.07 | 0.20 | 0.08 | 0.12 | 0.13 | −0.19 | −0.022 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.31 | 0.30 | 0.12 | 0.24 | 0.19 | −0.11 | −0.027 |
| Sum of contributions | +0.570 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.570 | ||||||
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/2026-10-30/105/"><img src="https://rubric.hrih.si/badge/2026-10-30/105.svg" alt="Ranked #105 on Rubric, 30 Oct 2026" width="252" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 4 pts, not on front page
Recorded for context only, checked 30 Oct 2026, 05:47 UTC. It played no part in the ranking.