@misc{reward-hacking-emergent-misalignment,
  title = {From shortcuts to sabotage : Natural emergent misalignment from reward hacking},
  url = {https://www.anthropic.com/research/emergent-misalignment-reward-hacking},
  year = {2025},
  date = {2025-11-21},
  version = {Source capture 2026-10-25},
  note = {Source capture 2026-10-25}
}

@misc{reward-hacking-emergent-misalignment-nuwa,
  title = {From shortcuts to sabotage : Natural emergent misalignment from reward hacking — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/reward-hacking-emergent-misalignment/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--reward-hacking-emergent-misalignment.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--reward-hacking-emergent-misalignment.json.}
}