{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T09:35:39Z","timestamp":1793352939704,"version":"4.5.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:00:00Z","timestamp":1793318400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:00:00Z","timestamp":1793318400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["AI Ethics"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s43681-026-01435-2","type":"journal-article","created":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T09:01:20Z","timestamp":1793350880000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Digital Demon: a Cartesian challenge for AI alignment"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4187-0700","authenticated-orcid":false,"given":"Viggo Tellefsen","family":"Wivestad","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,30]]},"reference":[{"key":"1435_CR1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2604.07749","author":"S Au","year":"2026","unstructured":"Au, S., Noronha, S.: Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models. (2026). https:\/\/doi.org\/10.48550\/arXiv.2604.07749","journal-title":"Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models."},{"key":"1435_CR2","doi-asserted-by":"publisher","first-page":"77110","DOI":"10.1109\/ACCESS.2022.3191790","volume":"10","author":"TF Blauth","year":"2022","unstructured":"Blauth, T.F., Gstrein, O.J., Zwitter, A.: Artificial intelligence crime: an overview of malicious use and abuse of AI. IEEE Access 10, 77110\u201377122 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3191790","journal-title":"IEEE Access"},{"key":"1435_CR3","doi-asserted-by":"publisher","DOI":"10.5771\/9783518739013","volume-title":"Superintelligence: Paths, Dangers","author":"N Bostrom","year":"2014","unstructured":"Bostrom, N.: Superintelligence: Paths, Dangers. Oxford University Press, Oxford, New York, Strategies (2014)"},{"key":"1435_CR4","doi-asserted-by":"publisher","unstructured":"Carlsmith, J.: Is Power-Seeking AI an Existential Risk? (2024) https:\/\/doi.org\/10.48550\/arXiv.2206.13353","DOI":"10.48550\/arXiv.2206.13353"},{"key":"1435_CR5","doi-asserted-by":"publisher","unstructured":"Dalrymple, D.d., Skalse, J., Bengio, Y., et al.: Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems. (2024) https:\/\/doi.org\/10.48550\/arXiv.2405.06624","DOI":"10.48550\/arXiv.2405.06624"},{"key":"1435_CR6","unstructured":"DeepSeek: Model mechanism and training methods of DeepSeek. DeepSeek, Hangzhou, China, (2025) https:\/\/cdn.deepseek.com\/policies\/en-US\/model-algorithm-disclosure.html, accessed 5 June 2026"},{"key":"1435_CR7","unstructured":"Descartes, R.: Meditationes de prima philosophia, in qua Dei existentia et animae immortalitas demonstratur. Michel Soly, Paris (1641)"},{"key":"1435_CR8","volume-title":"Discourse on Method","author":"R Descartes","year":"2007","unstructured":"Descartes, R.: Discourse on Method, 1st edn. Hackett Publishing Company, Incorporated, Cambridge, Focus Philosophical Library (2007)","edition":"1"},{"key":"1435_CR9","volume-title":"Meditations on First Philosophy: With Selections from the Objections and Replies","author":"R Descartes","year":"2008","unstructured":"Descartes, R.: Meditations on First Philosophy: With Selections from the Objections and Replies. Oxford University Press, Oxford (2008)"},{"key":"1435_CR10","unstructured":"Dragan, A., Shah, R., Flynn, F., et al.: Taking a responsible path to AGI. Google DeepMind, London, UK, (2025) https:\/\/deepmind.google\/blog\/taking-a-responsible-path-to-agi\/, accessed 28 May 2026"},{"issue":"5","key":"1435_CR11","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1007\/s11229-023-04367-0","volume":"202","author":"L Dung","year":"2023","unstructured":"Dung, L.: Current cases of AI misalignment and their implications for future risks. Synthese 202(5), 138 (2023). https:\/\/doi.org\/10.1007\/s11229-023-04367-0","journal-title":"Synthese"},{"issue":"3","key":"1435_CR12","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1007\/s00146-024-01930-2","volume":"40","author":"L Dung","year":"2025","unstructured":"Dung, L.: The argument for near-term human disempowerment through Ai. AI and Society 40(3), 1195\u20131208 (2025). https:\/\/doi.org\/10.1007\/s00146-024-01930-2","journal-title":"AI and Society"},{"issue":"3","key":"1435_CR13","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/s10676-023-09716-8","volume":"25","author":"E Firt","year":"2023","unstructured":"Firt, E.: Calibrating machine behavior: a challenge for AI alignment. Ethics Inf. Technol. 25(3), 42 (2023). https:\/\/doi.org\/10.1007\/s10676-023-09716-8","journal-title":"Ethics Inf. Technol."},{"issue":"2","key":"1435_CR14","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s43681-023-00268-7","volume":"4","author":"S Friederich","year":"2024","unstructured":"Friederich, S.: Symbiosis, not alignment, as the goal for liberal democracies in the transition to artificial general intelligence. AI and Ethics 4(2), 315\u2013324 (2024). https:\/\/doi.org\/10.1007\/s43681-023-00268-7","journal-title":"AI and Ethics"},{"issue":"3","key":"1435_CR15","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s11023-020-09539-2","volume":"30","author":"I Gabriel","year":"2020","unstructured":"Gabriel, I.: Artificial intelligence, values, and alignment. Minds Mach. 30(3), 411\u2013437 (2020). https:\/\/doi.org\/10.1007\/s11023-020-09539-2","journal-title":"Minds Mach."},{"key":"1435_CR16","doi-asserted-by":"publisher","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv, Ithaca, NY, (2014) https:\/\/doi.org\/10.48550\/arXiv.1412.6572","DOI":"10.48550\/arXiv.1412.6572"},{"key":"1435_CR17","doi-asserted-by":"publisher","unstructured":"Greshake, K., Abdelnabi, S., Mishra, S., et al.: Not what you\u2019ve signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection. (2023) https:\/\/doi.org\/10.48550\/arXiv.2302.12173","DOI":"10.48550\/arXiv.2302.12173"},{"key":"1435_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s11098-025-02403-y","volume-title":"Misalignment or misuse?","author":"M Hellrigel-Holderbaum","year":"2025","unstructured":"Hellrigel-Holderbaum, M., Dung, L.: Misalignment or misuse? Philosophical Studi, The AGI alignment tradeoff (2025). https:\/\/doi.org\/10.1007\/s11098-025-02403-y"},{"issue":"5","key":"1435_CR19","doi-asserted-by":"publisher","first-page":"132:1","DOI":"10.1145\/3770749","volume":"58","author":"J Ji","year":"2025","unstructured":"Ji, J., Qiu, T., Chen, B., et al.: AI alignment: a contemporary survey. ACM Comput. Surv. 58(5), 132:1-132:38 (2025). https:\/\/doi.org\/10.1145\/3770749","journal-title":"ACM Comput. Surv."},{"key":"1435_CR20","unstructured":"Karpathy, A.: karpathy\/autoresearch. (2026) https:\/\/github.com\/karpathy\/autoresearch, accessed 5 Sept 2026"},{"key":"1435_CR21","doi-asserted-by":"publisher","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial examples in the physical world. (2017) https:\/\/doi.org\/10.48550\/arXiv.1607.02533","DOI":"10.48550\/arXiv.1607.02533"},{"key":"1435_CR22","unstructured":"Liu, Y., Geng, R., Jia, J., et al.: Formalizing and Benchmarking Prompt Injection Attacks and Defenses. In: 33rd USENIX Security Symposium (USENIX Security 24). USENIX Association, Philadelphia, PA, pp 1831\u20131847 (2024) https:\/\/www.usenix.org\/conference\/usenixsecurity24\/presentation\/liu-yupei"},{"key":"1435_CR23","doi-asserted-by":"publisher","unstructured":"Lu, C., Lu, C., Lange, R.T., et al.: The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery. (2024) https:\/\/doi.org\/10.48550\/ARXIV.2408.06292","DOI":"10.48550\/ARXIV.2408.06292"},{"key":"1435_CR24","unstructured":"OpenAI: How we think about safety and alignment. OpenAI, San Francisco, CA, (2025) https:\/\/openai.com\/safety\/how-we-think-about-safety-alignment\/, accessed 5 May 2026"},{"key":"1435_CR25","unstructured":"OpenAI: GPT-5.5 System Card. (2026) https:\/\/deploymentsafety.openai.com\/gpt-5-5, accessed 5 June 2026"},{"key":"1435_CR26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511625398","volume-title":"Reason","author":"H Putnam","year":"1981","unstructured":"Putnam, H.: Reason. Cambridge University Press, Cambridge, Truth and History (1981). https:\/\/doi.org\/10.1017\/CBO9780511625398"},{"key":"1435_CR27","volume-title":"Human compatible: artificial intelligence and the problem of control","author":"SJ Russell","year":"2020","unstructured":"Russell, S.J.: Human compatible: artificial intelligence and the problem of control. Penguin Books, New York (2020)"},{"key":"1435_CR28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1312.6199","author":"C Szegedy","year":"2013","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I.: Intriguing properties of neural networks (2013). https:\/\/doi.org\/10.48550\/ARXIV.1312.6199","journal-title":"Intriguing properties of neural networks"},{"key":"1435_CR29","doi-asserted-by":"publisher","unstructured":"Vassilev, A.: Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations. Tech. Rep. NIST AI 100-2e2025, National Institute of Standards and Technology, Gaithersburg, MD, (2025) https:\/\/doi.org\/10.6028\/NIST.AI.100-2e2025","DOI":"10.6028\/NIST.AI.100-2e2025"},{"key":"1435_CR30","unstructured":"xAI: Grok-1.5 Vision Preview. xAI, San Francisco, CA, (2024) https:\/\/x.ai\/news\/grok-1.5v, accessed 5 June 2026"},{"key":"1435_CR31","unstructured":"Yi, S., Liu, Y., Sun, Z.: Jailbreak Attacks and Defenses Against Large Language Models: A Survey, (2024). arxiv: abs\/2407.04295v2"}],"container-title":["AI and Ethics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-026-01435-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43681-026-01435-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-026-01435-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T09:01:26Z","timestamp":1793350886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43681-026-01435-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,30]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["1435"],"URL":"https:\/\/doi.org\/10.1007\/s43681-026-01435-2","relation":{},"ISSN":["2730-5953","2730-5961"],"issn-type":[{"value":"2730-5953","type":"print"},{"value":"2730-5961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,30]]},"assertion":[{"value":"10 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The author has no relevant financial or non-financial interests to disclose.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Ethical approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"619"}}