AI 'hacker' finds 4 severe bugs in popular industrial control software in under 4 hours
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
An autonomous AI agent called Cipher, built by Causal Security, independently found and validated four previously unknown vulnerabilities in EPICS Base, an open-source toolkit used to run major scientific facilities, including particle accelerators and fusion experiments. The most severe flaw, rated 9.8 on CVSS, could allow remote code execution.
Why it ranked
No. 58 of 155 with a score of 0.62. The panel rated it highest on new information (0.89) and reader interest (0.82), lowest on audience breadth (0.52).
- AI judgeJudge 2claude-haiku-5-5
- Reports newsworthy CVEs in widely used EPICS software found by an AI agent; strong security and AI relevance, but excerpt is short and claims rest mostly on vendor and CISA reporting, with limited technical detail.
- AI judgeJudge 3gpt-5.6-luna
- Reports four severe EPICS vulnerabilities, CVE details, affected scientific infrastructure, remediation, and an autonomous discovery claim. Strong security relevance and practical urgency, though the excerpt is incomplete and partly relies on vendor-provided claims.
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
0.62total under rubric v2.2
- Significance0.65
- Reader interest0.82
- Audience breadth0.52
- Practical relevance0.71
- Substantiated0.59
- Technical depth0.55
- New information0.89
- Counts against: Promotional0.25
- Counts against: Overclaim0.28
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 | 0.58 | 0.60 | 0.78 | 0.65 | 0.20 | +0.24 | +0.157 |
| Reader interest | 0.74 | 0.80 | 0.92 | 0.82 | 0.18 | +0.26 | +0.213 |
| Audience breadth | 0.52 | 0.50 | 0.55 | 0.52 | 0.05 | +0.13 | +0.068 |
| Practical relevance | 0.62 | 0.70 | 0.82 | 0.71 | 0.20 | +0.22 | +0.157 |
| Substantiated | 0.50 | 0.60 | 0.67 | 0.59 | 0.17 | +0.05 | +0.029 |
| Technical depth | 0.68 | 0.40 | 0.57 | 0.55 | 0.28 | +0.05 | +0.028 |
| New information | 0.90 | 0.80 | 0.96 | 0.89 | 0.16 | +0.05 | +0.044 |
| Promotional | 0.12 | 0.20 | 0.42 | 0.25 | 0.30 | −0.19 | −0.047 |
| Overclaim | 0.26 | 0.30 | 0.28 | 0.28 | 0.04 | −0.11 | −0.031 |
| Sum of contributions | +0.619 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.619 | ||||||
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/2026-10-28/58/"><img src="https://rubric.hrih.si/badge/2026-10-28/58.svg" alt="Ranked #58 on Rubric, 28 Oct 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN —
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.