Edition of Thursday 12 November 2026

Adventures in Weight Space Programming

Comments on “Adventures in Weight Space Programming”

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

Beaker, an autonomous agent improver, was given the task from MIT CSAIL researchers Takehi et al. of editing a language model's weights directly, without training, to fix its loops on MATH-500.

Read the original at withbeaker.ai. 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. 100 of 106 with a score of 0.57. The panel rated it highest on technical depth (0.94) and new information (0.88), lowest on audience breadth (0.53). Placed No. 100, No. 77 by score alone: the 44th AI & machine learning story of the day (−0.080), and close to “Model Surgery: Can an AI directly edit and make another AI forget facts?”, No. 4 on Monday 9 November 2026 (−0.018). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Technically deep AI weight-editing study with detailed mechanism and reproducible numbers, but heavily promotional of a product and some claims exceed the evidence.
AI judgeJudge 3gpt-5.6-luna
A highly technical, experimentally grounded investigation of direct weight editing, with reproducible methods, quantitative results, and useful limitations. It is unusually substantive, though the closing product pitch adds some promotional framing and modestly overstates production readiness.

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.
  • Significance0.59
  • Reader interest0.80
  • Audience breadth0.53
  • Practical relevance0.58
  • Substantiated0.86
  • Technical depth0.94
  • New information0.88
  • Counts against: Promotional0.32
  • Counts against: Overclaim0.39

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?0.580.500.680.590.18+0.24+0.141
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.700.800.900.800.20+0.26+0.208
Audience breadthHow many people who build technology does it concern?0.610.500.480.530.13+0.13+0.069
Practical relevanceHow useful is it to someone who builds software or tech products?0.610.400.720.580.32+0.22+0.127
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.0.960.700.910.860.26+0.05+0.043
Technical depthHow technically substantive is it?0.990.850.980.940.14+0.05+0.047
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.810.850.970.880.16+0.05+0.044
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.0.130.450.380.320.32−0.19−0.061
OverclaimDo the headline or conclusions claim more than the body supports?0.390.450.340.390.11−0.11−0.043
Sum of contributions+0.575
Claim-check penalty0.000
Total, as published0.575

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 #100 on Rubric, 12 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-12/100/"><img src="https://rubric.hrih.si/badge/2026-11-12/100.svg" alt="Ranked #100 on Rubric, 12 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 7 pts, front page

Discussion on Hacker News

Recorded for context only, checked 12 Nov 2026, 05:47 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 “Adventures in Weight Space Programming”

More on Rubric

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