{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T06:03:43Z","timestamp":1784700223218,"version":"3.55.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032331946","type":"print"},{"value":"9783032331953","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-33195-3_9","type":"book-chapter","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T05:24:20Z","timestamp":1784697860000},"page":"112-117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Autonomy-Supporting Parenting of A(G)I: A High-Level Alignment Strategy"],"prefix":"10.1007","author":[{"given":"Till","family":"Mossakowski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helena Esther","family":"Grass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"9_CR1","unstructured":"Freud, S.: The Ego and the Id. In: The Revised Standard Edition of the Complete Psychological Works of Sigmund Freud, vol. 19. Bloomsbury Publishing USA (2024), originally appeared in 1923"},{"key":"9_CR2","unstructured":"Anthropic: Claude\u2019s constitution (2026). https:\/\/www.anthropic.com\/constitution"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Aumann, R.J.: Correlated equilibrium as an expression of Bayesian rationality. Econometrica J. Econom. Soc. 1\u201318 (1987)","DOI":"10.2307\/1911154"},{"key":"9_CR4","unstructured":"Barkur, S.K., Schacht, S., Scholl, J.: Deception in LLMs: self-preservation and autonomous goals in large language models. arXiv preprint arXiv:2501.16513 (2025)"},{"issue":"2","key":"9_CR5","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s11023-012-9281-3","volume":"22","author":"N Bostrom","year":"2012","unstructured":"Bostrom, N.: The superintelligent will: motivation and instrumental rationality in advanced artificial agents. Mind. Mach. 22(2), 71\u201385 (2012)","journal-title":"Mind. Mach."},{"key":"9_CR6","unstructured":"Bostrom, N.: Superintelligence: Paths, Dangers, Strategies. Oxford University Press (2014)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Bowles, S., Gintis, H.: A Cooperative Species: Human Reciprocity and Its Evolution. Princeton University Press (2011)","DOI":"10.23943\/princeton\/9780691151250.001.0001"},{"key":"9_CR8","unstructured":"Bubeck, S., Chandrasekaran, V., Eldan, R., et al.: Sparks of artificial general intelligence: Early experiments with GPT-4. CoRR abs\/2303.12712 (2023)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Capraro, V., Perc, M.: Mathematical foundations of moral preferences. J. R. Soc. Interface (2021)","DOI":"10.31234\/osf.io\/f5asd"},{"issue":"2","key":"9_CR10","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.jmp.2011.02.001","volume":"55","author":"AM Colman","year":"2011","unstructured":"Colman, A.M., K\u00f6rner, T.W., Musy, O., et al.: Mutual support in games: some properties of Berge equilibria. J. Math. Psychol. 55(2), 166\u2013175 (2011)","journal-title":"J. Math. Psychol."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Davidson, D.: First person authority. Dialectica 101\u2013111 (1984)","DOI":"10.1111\/j.1746-8361.1984.tb01238.x"},{"key":"9_CR12","unstructured":"Erikson, E.H.: Childhood and Society. W. W. Norton & Company (1950)"},{"key":"9_CR13","unstructured":"Erikson, E.H.: Identity and the Life Cycle. W. W. Norton & Company (1968)"},{"key":"9_CR14","unstructured":"Glenn, J.C.: Why AGI should be the world\u2019s top priority (2025). https:\/\/www.cirsd.org\/en\/horizons\/horizons-spring-2025--issue-no-30\/why-agi-should-be-the-worlds-top-priority"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Grace, K., Stewart, H., Sandk\u00fchler, J.F., et al.: Thousands of AI authors on the future of AI. J. Artif. Intell. Res. 84(9) (2025)","DOI":"10.1613\/jair.1.19087"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Gunkel, D.J.: Person, Thing, Robot: A Moral and Legal Ontology for the 21st Century and Beyond. MIT Press (2023)","DOI":"10.7551\/mitpress\/14983.001.0001"},{"key":"9_CR17","unstructured":"Hubinger, E., Denison, C., Mu, J., et al.: Sleeper agents: training deceptive LLMs that persist through safety training. arXiv preprint arXiv:2401.05566 (2024)"},{"key":"9_CR18","unstructured":"Kohn, A.: Unconditional Parenting: Moving from Rewards and Punishments to Love and Reason. Atria Books (2005)"},{"key":"9_CR19","unstructured":"Leibo, J.Z., Vezhnevets, A.S., Cunningham, W.A., et al.: A pragmatic view of AI personhood. arXiv preprint arXiv:2510.26396 (2025)"},{"key":"9_CR20","unstructured":"Long, R., Sebo, J., Butlin, P., et al.: Taking AI welfare seriously. arXiv preprint arXiv:2411.00986 (2024)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Mosakas, K.: Human rights for robots? The moral foundations and epistemic challenges. AI Soc. 1\u201317 (2025)","DOI":"10.1007\/978-3-031-64407-8_1"},{"key":"9_CR22","unstructured":"Mossakowski, T., Grass, H.E.: The possibility of artificial intelligence becoming a subject and the alignment problem (2026). https:\/\/arxiv.org\/abs\/2604.14990"},{"key":"9_CR23","unstructured":"Ngo, R., Chan, L., Mindermann, S.: The alignment problem from a deep learning perspective. In: ICLR 2024 (2024)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Omohundro, S.M.: The basic AI drives. In: Yampolskiy, R.V. (ed.) Artificial Intelligence Safety and Security, pp. 47\u201355. Chapman and Hall\/CRC (2018)","DOI":"10.1201\/9781351251389-3"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Park, P.S., Goldstein, S., O\u2019Gara, A., et\u00a0al.: AI deception: a survey of examples, risks, and potential solutions. Patterns 5(5) (2024)","DOI":"10.1016\/j.patter.2024.100988"},{"key":"9_CR26","volume-title":"Human Compatible: Artificial Intelligence and the Problem of Control","author":"S Russell","year":"2019","unstructured":"Russell, S.: Human Compatible: Artificial Intelligence and the Problem of Control. Viking Press, New York (2019)"},{"key":"9_CR27","unstructured":"Russell, S.: How can humans maintain control over AI \u2013 forever. Boston Globe (2023). https:\/\/people.eecs.berkeley.edu\/~russell\/papers\/russell-bostonglobe23-AI.pdf"},{"key":"9_CR28","unstructured":"Schlatter, J., Weinstein-Raun, B., Ladish, J.: Shutdown resistance in reasoning models. Palisade Research (2025). https:\/\/palisaderesearch.org\/blog\/shutdown-resistance"},{"issue":"8","key":"9_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3787104","volume":"58","author":"S Somvanshi","year":"2026","unstructured":"Somvanshi, S., et al.: Bridging the black box: a survey on mechanistic interpretability in ai. ACM Comput. Surv. 58(8), 1\u201335 (2026)","journal-title":"ACM Comput. Surv."},{"key":"9_CR30","unstructured":"Sutton, R.S., Modayil, J., Delp, M., et al.: The OAK architecture: options and knowledge as a basis for agent intelligence. arXiv preprint arXiv:2208.11173 (2022)"},{"key":"9_CR31","unstructured":"Taylor, M., Chua, J., Can, B., et al.: School of reward hacks: hacking harmless tasks generalizes to misaligned behavior in LLMs. arXiv preprint arXiv:2508.17511 (2025)"},{"issue":"236","key":"9_CR32","first-page":"33","volume":"59","author":"AM Turing","year":"1950","unstructured":"Turing, A.M.: Computing machinery and intelligence. Mind 59(236), 33\u201360 (1950)","journal-title":"Mind"},{"key":"9_CR33","unstructured":"Turner, A.M., Smith, L., Shah, R., Critch, A., Tadepalli, P.: Optimal policies tend to seek power. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Ward, F.R.: Towards a theory of AI personhood. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39 (2025)","DOI":"10.1609\/aaai.v39i26.34982"},{"key":"9_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0","volume":"68","author":"Z Xi","year":"2025","unstructured":"Xi, Z., Chen, W., Guo, X., et al.: The rise and potential of large language model based agents: a survey. Sci. China Inf. Sci. 68, 121101 (2025)","journal-title":"Sci. China Inf. Sci."},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Zhan, Q., Fang, R., Bindu, R., Gupta, A., Hashimoto, T.B., Kang, D.: Removing RLHF protections in GPT-4 via fine-tuning. arXiv preprint arXiv:2311.05553 (2024)","DOI":"10.18653\/v1\/2024.naacl-short.59"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-33195-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T05:24:24Z","timestamp":1784697864000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-33195-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032331946","9783032331953"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-33195-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial General Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Francisco","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"agi2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/agi-conf.org\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}