A Working Nintendo in ~1GB of Qwen Weights
Comments on “A Working Nintendo in ~1GB of Qwen Weights”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
The project nesformer runs a working NES, including its 6502 CPU, work RAM and game cartridge code, inside the weights of an unmodified Qwen3.5 model, with no training involved.
Why it ranked
No. 74 of 111 with a score of 0.59. The panel rated it highest on technical depth (0.96) and new information (0.94), lowest on practical relevance (0.45). Placed No. 74, No. 65 by score alone: the 22nd 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
- Novel, technically deep project compiling a 6502 CPU and NES into LLM weights; verified against reference emulator. Strong hobbyist/research interest, but limited practical use and broad significance for builders.
- AI judgeJudge 3gpt-5.6-luna
- A highly technical, reproducible project compiles a 6502 NES CPU into sparse Qwen weights, with detailed architecture, limitations, tests, benchmarks, and exact emulator comparisons. It is novel and compelling, though mainly a niche demonstration rather than broadly actionable infrastructure.
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
0.59total under rubric v2.3
- Significance0.51
- Reader interest0.79
- Audience breadth0.47
- Practical relevance0.45
- Substantiated0.90
- Technical depth0.96
- New information0.94
- Counts against: Promotional0.04
- Counts against: Overclaim0.23
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? | 0.49 | 0.45 | 0.58 | 0.51 | 0.13 | +0.24 | +0.121 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.67 | 0.80 | 0.90 | 0.79 | 0.23 | +0.26 | +0.205 |
| Audience breadthHow many people who build technology does it concern? | 0.43 | 0.60 | 0.38 | 0.47 | 0.22 | +0.13 | +0.061 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.47 | 0.35 | 0.52 | 0.45 | 0.17 | +0.22 | +0.098 |
| 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. | 0.99 | 0.80 | 0.90 | 0.90 | 0.19 | +0.05 | +0.045 |
| Technical depthHow technically substantive is it? | 1.00 | 0.90 | 0.98 | 0.96 | 0.10 | +0.05 | +0.048 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.92 | 0.90 | 0.99 | 0.94 | 0.09 | +0.05 | +0.047 |
| 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. | 0.05 | 0.05 | 0.03 | 0.04 | 0.02 | −0.19 | −0.008 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.44 | 0.20 | 0.04 | 0.23 | 0.40 | −0.11 | −0.025 |
| Sum of contributions | +0.593 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.593 | ||||||
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/2026-10-31/74/"><img src="https://rubric.hrih.si/badge/2026-10-31/74.svg" alt="Ranked #74 on Rubric, 31 Oct 2026" width="245" height="28"></a>Also covered by
Elsewhere
Elsewhere: HN 226 pts, front page
Recorded for context only, checked 31 Oct 2026, 05:46 UTC. It played no part in the ranking.