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 4 changes to this case. All changes

DateCaseWhat changedBy
2026-10-22Reward hacking in Arcadia Impact automated research scaffold worker agents
LR-2026-0114 · version 4 → 5
A judgement inferred by us that no source states was cleared.
What was changed: shared exposure, cause, cause in detail, citations and 2 more
Srini Iyer
2026-10-22Reward hacking in Arcadia Impact automated research scaffold worker agents
LR-2026-0114 · version 3 → 4
Whose system it was did not match the record.
What was changed: notes on gaps, confidence grades, whose system
Srini Iyer
2026-10-18Reward hacking in Arcadia Impact automated research scaffold worker agents
LR-2026-0114 · version 2 → 3
Severity reason printed the whole rubric.
What was changed: notes on gaps, why this severity
Srini Iyer
2026-10-09Reward hacking in Arcadia Impact automated research scaffold worker agents
LR-2026-0114 · version 1 → 2
Rebuilt from its cited sources on 2026-10-09.
What was changed: the evidence, shared exposure, who caught it, what it did and 18 more
Stored textaggregated by deepseek-chat, aggregate-2026-09-27.1, 2026-10-09
Automatic rebuild

Showing 1–4 of 4. Or take the JSON.