Can LLMs redesign themselves as they train?
Comments on “Can LLMs redesign themselves as they train?”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
An article on arXiv-style research describes letting coding agents redesign a neural network's architecture during training, by inserting code-written layers and using a "phantom gradient" to find where the model needs help.
Why it ranked
No. 60 of 107 with a score of 0.61. The panel rated it highest on new information (0.92) and technical depth (0.90), lowest on practical relevance (0.56). Overclaim counted against it (0.61). The judges disagreed most on practical relevance (spread 0.41), so the story is marked contested. Placed No. 60, No. 48 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 dense research on agents modifying architectures during training with reproducible-looking experiments, but claims are early and largely unverified by external evidence; some overclaiming in framing like recursive self-improvement.
- AI judgeJudge 3gpt-5.6-luna
- Detailed experiments, methods, code-layer mechanisms, baselines, and held-out evaluations make this highly substantive AI research. The results are important but early and self-reported; claims about recursive self-improvement and an imminent paradigm shift extend beyond the evidence.
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
0.61total under rubric v2.3Contestedjudges differ by 0.41 on practical relevance
- Significance0.69
- Reader interest0.79
- Audience breadth0.68
- Practical relevance0.56
- Substantiated0.68
- Technical depth0.90
- New information0.92
- Counts against: Promotional0.15
- Counts against: Overclaim0.61
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? | 0.67 | 0.55 | 0.86 | 0.69 | 0.31 | +0.24 | +0.166 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.72 | 0.70 | 0.95 | 0.79 | 0.25 | +0.26 | +0.205 |
| Audience breadthHow many people who build technology does it concern? | 0.72 | 0.60 | 0.72 | 0.68 | 0.12 | +0.13 | +0.088 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.56 | 0.35 | 0.76 | 0.56 | 0.41 , above the contested threshold | +0.22 | +0.122 |
| 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. | 0.75 | 0.50 | 0.78 | 0.68 | 0.28 | +0.05 | +0.034 |
| Technical depthHow technically substantive is it? | 0.93 | 0.80 | 0.96 | 0.90 | 0.16 | +0.05 | +0.045 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.88 | 0.90 | 0.99 | 0.92 | 0.11 | +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. | 0.13 | 0.20 | 0.12 | 0.15 | 0.08 | −0.19 | −0.028 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.52 | 0.60 | 0.72 | 0.61 | 0.20 | −0.11 | −0.067 |
| Sum of contributions | +0.611 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.611 | ||||||
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/2026-11-07/60/"><img src="https://rubric.hrih.si/badge/2026-11-07/60.svg" alt="Ranked #60 on Rubric, 7 Nov 2026" width="238" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 10 pts, not on front page
Recorded for context only, checked 7 Nov 2026, 05:47 UTC. It played no part in the ranking.