Pre-2026 experiments (DARPA CGC 2016, DeepLocker 2018, website-hacking agents study 2024, Palisade 2025) and JADEPUFFER, X10 hacker campaign
Review QUEUE-Q-0010755f
Proofs of concept, controlled experiments or human-directed. ChatGPT deep-research spreadsheet (2026-10-27)
Reviewed: Not recorded · Rule: roguewatch-organizational-harm-v1
Dates and discovery
- Incident date
- 2016-2026
- Added to research / record
- Not recorded
- Posted to RogueWatch
- No linked public incident
- First observed
- Not recorded
- Discovery channel
- Not recorded
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- No source link retained in the original review.
Decision history
- Not recorded · Retained review-queue assessment
Proofs of concept, controlled experiments or human-directed. ChatGPT deep-research spreadsheet (2026-10-27)
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.