@misc{school-of-reward-hacks,
  title = {School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs},
  url = {https://truthful.ai/papers/school-of-reward-hacks/},
  author = {Mia Taylor and James Chua and Jan Betley and Johannes Treutlein and Owain Evans},
  year = {2025},
  date = {2025-08-25},
  version = {Source capture 2026-10-25},
  note = {Source capture 2026-10-25}
}

@misc{school-of-reward-hacks-nuwa,
  title = {School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/school-of-reward-hacks/},
  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--school-of-reward-hacks.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--school-of-reward-hacks.json.}
}