AI Models Can Provably Hide Arbitrary Capabilities
Comments on “AI Models Can Provably Hide Arbitrary Capabilities”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
Researchers Andis Draguns, Sumeet Ramesh Motwani, Christian Schroeder de Witt and Raymond Douglas show that a second neural network can be hidden inside a model's weights using cryptographic lockers, so that it runs only when a secret trigger appears in the input.
Why it ranked
No. 50 of 124 with a score of 0.62. The panel rated it highest on new information (0.94) and reader interest (0.84), lowest on practical relevance (0.66). Older work: a freshness penalty of 0.100.
Every answer behind this is in the table under Score.
Score
0.62total under rubric v2.2
- Significance0.70
- Reader interest0.84
- Audience breadth0.72
- Practical relevance0.66
- Substantiated0.83
- Technical depth0.83
- New information0.94
- Counts against: Promotional0.04
- Counts against: Overclaim0.26
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) |
|---|---|---|---|---|---|---|---|
| Significance | 0.71 | 0.62 | 0.78 | 0.70 | 0.16 | +0.24 | +0.169 |
| Reader interest | 0.77 | 0.80 | 0.95 | 0.84 | 0.18 | +0.26 | +0.218 |
| Audience breadth | 0.78 | 0.70 | 0.68 | 0.72 | 0.10 | +0.13 | +0.094 |
| Practical relevance | 0.65 | 0.55 | 0.78 | 0.66 | 0.23 | +0.22 | +0.145 |
| Substantiated | 0.81 | 0.80 | 0.88 | 0.83 | 0.08 | +0.05 | +0.042 |
| Technical depth | 0.78 | 0.80 | 0.90 | 0.83 | 0.12 | +0.05 | +0.041 |
| New information | 0.90 | 0.95 | 0.98 | 0.94 | 0.08 | +0.05 | +0.047 |
| Promotional | 0.07 | 0.03 | 0.01 | 0.04 | 0.06 | −0.19 | −0.007 |
| Overclaim | 0.41 | 0.20 | 0.18 | 0.26 | 0.23 | −0.11 | −0.029 |
| Sum of contributions | +0.720 | ||||||
| Freshness penalty | −0.100 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.620 | ||||||
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 freshness penalty is for older work: this one was first published 14 Oct 2026.
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/2026-10-27/50/"><img src="https://rubric.hrih.si/badge/2026-10-27/50.svg" alt="Ranked #50 on Rubric, 27 Oct 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 27 Oct 2026, 05:46 UTC. It played no part in the ranking.