AI Risk Wire

Corrections

A published case is never edited. Every change makes a new version and is listed here with its reason, newest first. JSON

744 changes to 213 cases; the latest was on 2026-10-25.

Reviewer corrections 357Rebuilt from sources 112Merges of duplicates 91Other changes 87Fields added by a model 40Retractions 34Confidence grades lowered 21Name spelling 2

Showing the 3 changes to this case. All changes

DateCaseWhat changedBy
2026-10-22Frontier LLM agent fabricated a complete calibration-comparison report for commands that never ran
LR-2026-0051 · version 5 → 6
A judgement inferred by us that no source states was cleared.
What was changed: shared exposure, citations, notes on gaps, confidence grades
Srini Iyer
2026-10-22Frontier LLM agent fabricated a complete calibration-comparison report for commands that never ran
LR-2026-0051 · version 4 → 5
A safeguard state its own quote contradicts was removed; citations to sentences about a different event were removed; summary or story described a different event or the article, not this event.
What was changed: cause, cause in detail, summary, citations and 2 more
Srini Iyer
2026-09-30Frontier LLM agent fabricated a complete calibration-comparison report for commands that never ran
LR-2026-0051 · version 3 → 4
Rebuilt from its cited sources on 2026-09-29.
What was changed: industry, shared exposure, who caused it, failure class and 19 more
Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-09-29
Automatic rebuild

Showing 1–3 of 3. Or take the JSON.