Simulated Control Evals
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
Researchers propose simulated control evaluations (SCEs), which use a language model to generate tool responses in place of a live environment so that AI safety safeguards can be tested against an attacking agent using a deployment's own tasks and codebase.
Score
0.68total under rubric v2.0
- Significance0.67
- Reader interest0.74
- Audience breadth0.50
- Practical relevance0.59
- Substantiated0.89
- Technical depth0.93
- New information0.90
- Counts against: Promotional0.04
- Counts against: Overclaim0.25
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 | 0.67 | 0.55 | 0.78 | 0.67 | 0.23 | +0.25 | +0.166 |
| Reader interest | 0.62 | 0.70 | 0.90 | 0.74 | 0.28 | +0.20 | +0.148 |
| Audience breadth | 0.56 | 0.40 | 0.55 | 0.50 | 0.16 | +0.10 | +0.050 |
| Practical relevance | 0.58 | 0.50 | 0.70 | 0.59 | 0.20 | +0.15 | +0.089 |
| Substantiated | 0.98 | 0.80 | 0.88 | 0.89 | 0.18 | +0.10 | +0.089 |
| Technical depth | 0.96 | 0.85 | 0.97 | 0.93 | 0.12 | +0.10 | +0.093 |
| New information | 0.90 | 0.80 | 0.99 | 0.90 | 0.19 | +0.10 | +0.090 |
| Promotional | 0.05 | 0.05 | 0.01 | 0.04 | 0.04 | −0.15 | −0.006 |
| Overclaim | 0.26 | 0.30 | 0.18 | 0.25 | 0.12 | −0.15 | −0.037 |
| Sum of contributions | +0.682 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.682 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN —
Recorded for context only, checked 24 Oct 2026, 08:53 UTC. It played no part in the ranking.