{"entities":[{"id":"inner-or-deceptive-misalignment","name":"Inner or deceptive misalignment","type":"concept","proposition":{"code":"R03","criterion":"A system produced by training or search can come to pursue an objective other than the one its training specified (the training signal or loss), while performing well on that training objective; an objective that is only misspecified by its developers does not meet the criterion; this includes, but is not limited to, a system that behaves as aligned during training or evaluation in order to pursue another objective later.","terms":["inner alignment","inner misalignment","mesa-optimizer","mesa-optimiser","deceptive alignment","goal misgeneralization","goal misgeneralisation","alignment faking"]}},{"id":"langosco-2021-goal-misgeneralization","name":"Objective Robustness in Deep Reinforcement Learning (later: Goal Misgeneralization in Deep Reinforcement Learning)","type":"document","subtype":"Preprint","description":"A preprint by Jack Koch and 4 co-authors, arXiv preprint 2105.14111, dated 28 May 2021. arXiv v1 stamp, 28 May 2021.","sourceIds":["source-rd-langosco-2021-goal-misgeneralization"]}],"claims":[{"id":"rd-r03-langosco-2021-goal-misgeneralization","subject":"langosco-2021-goal-misgeneralization","predicate":"articulates_proposition","object":{"kind":"entity","entityId":"inner-or-deceptive-misalignment"},"topic":"ideas","statement":"Koch, Langosco, Pfau, Le and Sharkey's paper of May 2021 states that a reinforcement-learning agent can keep the capabilities it had in training while pursuing an objective other than the true reward off-distribution, and reports demonstrations of this in deep RL agents.","time":{"kind":"event","date":"2021-05-28","basis":"publication","note":"Date of the arXiv v1 submission."},"derivation":"explicit","resolution":"supported","editorialState":"seed","evidenceIds":["evidence-rd-r03-langosco-2021-goal-misgeneralization-1","evidence-rd-r03-langosco-2021-goal-misgeneralization-2"],"attributes":{"thought":{"roles":["articulation"],"register":"nonfiction"}}}],"sources":[{"id":"source-rd-langosco-2021-goal-misgeneralization","documentId":"langosco-2021-goal-misgeneralization","title":"Objective Robustness in Deep Reinforcement Learning","authors":["Jack Koch","Lauro Langosco","Jacob Pfau","James Le","Lee Sharkey"],"publisher":"arXiv preprint 2105.14111","publicationDate":"2021-05-28","version":"Retrieved for the candidate pack on 2026-10-29 (SHA-256 7e4712b3f06d5f6f3e7101fc9e7710e30f36464c482d03ce14e8398cfadbde33). arXiv v1 of 28 May 2021, titled \"Objective Robustness in Deep Reinforcement Learning\"; later versions retitled \"Goal Misgeneralization in Deep Reinforcement Learning\" (ICML 2022).","evidenceUrl":"https://arxiv.org/pdf/2105.14111v1","language":"en"}],"evidence":[{"id":"evidence-rd-r03-langosco-2021-goal-misgeneralization-1","claimId":"rd-r03-langosco-2021-goal-misgeneralization","sourceId":"source-rd-langosco-2021-goal-misgeneralization","sourceRole":"primary","support":"supports","verification":"machine_checked","retrievalRoute":"direct"},{"id":"evidence-rd-r03-langosco-2021-goal-misgeneralization-2","claimId":"rd-r03-langosco-2021-goal-misgeneralization","sourceId":"source-rd-langosco-2021-goal-misgeneralization","support":"supports","verification":"machine_checked","retrievalRoute":"direct"}],"at":{"entities":[1851,1861],"claims":[5150],"sources":[1765],"evidence":[6832,6833]},"index":{"byClaim":[["rd-r03-langosco-2021-goal-misgeneralization",["propositions:risk-debate"]]],"marks":[],"chronicle":{"years":[{"year":1863,"topics":{"ideas":5},"stated":0},{"year":1865,"topics":{"ideas":1},"stated":0},{"year":1872,"topics":{"ideas":7},"stated":0},{"year":1943,"topics":{"ideas":1},"stated":0},{"year":1947,"topics":{"ideas":2},"stated":0},{"year":1950,"topics":{"ideas":7},"stated":0},{"year":1951,"topics":{"ideas":5},"stated":0},{"year":1952,"topics":{"ideas":2},"stated":0},{"year":1955,"topics":{"ideas":31},"stated":0},{"year":1956,"topics":{"ideas":1},"stated":0},{"year":1957,"topics":{"ideas":1},"stated":0},{"year":1958,"topics":{"ideas":3},"stated":0},{"year":1959,"topics":{"ideas":6},"stated":0},{"year":1960,"topics":{"ideas":11},"stated":0},{"year":1961,"topics":{"ideas":10},"stated":0},{"year":1965,"topics":{"ideas":8},"stated":0},{"year":1966,"topics":{"ideas":20},"stated":0},{"year":1968,"topics":{"ideas":5},"stated":0},{"year":1969,"topics":{"ideas":2},"stated":0},{"year":1971,"topics":{"ideas":4},"stated":0},{"year":1972,"topics":{"ideas":1},"stated":0},{"year":1973,"topics":{"ideas":2},"stated":0},{"year":1974,"topics":{"ideas":2},"stated":0},{"year":1975,"topics":{"ideas":1},"stated":0},{"year":1976,"topics":{"ideas":1},"stated":0},{"year":1977,"topics":{"people":2,"ideas":8},"stated":0},{"year":1979,"topics":{"ideas":4},"stated":0},{"year":1980,"topics":{"ideas":2},"stated":0},{"year":1981,"topics":{"people":2},"stated":0},{"year":1982,"topics":{"ideas":4},"stated":0},{"year":1983,"topics":{"ideas":4},"stated":0},{"year":1984,"topics":{"ideas":21},"stated":0},{"year":1985,"topics":{"ideas":9},"stated":0},{"year":1986,"topics":{"ideas":18},"stated":0},{"year":1987,"topics":{"ideas":1},"stated":0},{"year":1988,"topics":{"ideas":6},"stated":0},{"year":1989,"topics":{"ideas":8},"stated":0},{"year":1990,"topics":{"ideas":5},"stated":0},{"year":1991,"topics":{"ideas":11},"stated":0},{"year":1992,"topics":{"ideas":9},"stated":0},{"year":1993,"topics":{"ideas":14,"people":3},"stated":0},{"year":1994,"topics":{"ideas":14},"stated":0},{"year":1995,"topics":{"ideas":10,"people":1},"stated":0},{"year":1996,"topics":{"ideas":71},"stated":0},{"year":1997,"topics":{"ideas":12},"stated":0},{"year":1998,"topics":{"ideas":49},"stated":0},{"year":1999,"topics":{"ideas":27,"people":1,"institutions":1},"stated":0},{"year":2000,"topics":{"ideas":62},"stated":0},{"year":2001,"topics":{"ideas":39},"stated":0},{"year":2002,"topics":{"ideas":30},"stated":0},{"year":2003,"topics":{"ideas":8},"stated":0},{"year":2004,"topics":{"ideas":12,"people":3},"stated":0},{"year":2005,"topics":{"ideas":10,"people":1},"stated":0},{"year":2006,"topics":{"ideas":26,"people":1},"stated":0},{"year":2007,"topics":{"ideas":20},"stated":0},{"year":2008,"topics":{"ideas":57,"people":3,"institutions":1},"stated":0},{"year":2009,"topics":{"ideas":10,"people":1},"stated":0},{"year":2010,"topics":{"people":3,"ideas":11,"institutions":1,"governance":4},"stated":0},{"year":2011,"topics":{"people":3,"ideas":7,"institutions":2},"stated":0},{"year":2012,"topics":{"people":4,"ideas":17,"institutions":2},"stated":0},{"year":2013,"topics":{"ideas":46,"people":4,"institutions":2,"capital":1},"stated":0},{"year":2014,"topics":{"institutions":2,"ideas":54,"people":5},"stated":0},{"year":2015,"topics":{"people":22,"ideas":122,"institutions":3,"capital":1},"stated":0},{"year":2016,"topics":{"ideas":88,"people":2},"stated":0},{"year":2017,"topics":{"people":16,"institutions":2,"ideas":128,"governance":2},"stated":0},{"year":2018,"topics":{"people":8,"ideas":158,"institutions":8,"governance":1},"stated":0},{"year":2019,"topics":{"capital":1,"compute":1,"people":10,"governance":19,"ideas":175,"institutions":4},"stated":0},{"year":2020,"topics":{"people":6,"ideas":98,"institutions":1,"governance":2},"stated":0},{"year":2021,"topics":{"people":27,"ideas":177,"compute":1,"institutions":23,"governance":4,"capital":6},"stated":0},{"year":2022,"topics":{"people":15,"ideas":217,"institutions":6,"governance":3,"compute":2,"capital":1},"stated":0},{"year":2023,"topics":{"capital":5,"compute":7,"institutions":23,"people":51,"governance":179,"ideas":389},"stated":0},{"year":2024,"topics":{"capital":12,"compute":19,"governance":282,"people":80,"ideas":178,"institutions":28},"stated":1},{"year":2025,"topics":{"governance":547,"compute":69,"capital":34,"people":90,"institutions":18,"ideas":178},"stated":7},{"year":2026,"topics":{"governance":442,"capital":8,"compute":32,"institutions":21,"ideas":91,"people":107},"stated":19},{"year":2027,"topics":{},"stated":9},{"year":2028,"topics":{},"stated":6},{"year":2029,"topics":{},"stated":3},{"year":2030,"topics":{},"stated":3},{"year":2032,"topics":{},"stated":2},{"year":2035,"topics":{},"stated":2},{"year":2039,"topics":{},"stated":1},{"year":2042,"topics":{},"stated":1},{"year":2050,"topics":{},"stated":1}],"scheduled":[],"statedBy":[]},"collections":[{"target":{"kind":"propositions","id":"superintelligence"},"title":"Propositions about superintelligence, 1863–2022","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"risk-debate"},"title":"Arguments about catastrophic risk from advanced AI","claimIds":["rd-r03-langosco-2021-goal-misgeneralization"],"records":[]},{"target":{"kind":"propositions","id":"yudkowsky-arguments"},"title":"Eliezer Yudkowsky’s arguments on common claims about AI, 1996–2026","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"economics-of-machine-intelligence"},"title":"Economics of machine intelligence","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"orbital-compute-arguments"},"title":"Arguments about compute in orbit","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"ai-bio-arguments"},"title":"Arguments about AI and biological risk","claimIds":[],"records":[]},{"target":{"kind":"propositions","id":"ai-in-science"},"title":"AI in science","claimIds":[],"records":[]},{"target":{"kind":"documents"},"title":"Frontier safety frameworks","claimIds":[]},{"target":{"kind":"compare","id":"frontier-safety-frameworks"},"title":"Compare frameworks","claimIds":[]},{"target":{"kind":"control","id":"openai"},"title":"OpenAI’s control structure, 2015–2026","claimIds":[]},{"target":{"kind":"control","id":"anthropic"},"title":"Anthropic’s control structure, 2021–2026","claimIds":[]},{"target":{"kind":"commitments"},"title":"External commitments and obligations","claimIds":[]},{"target":{"kind":"question","id":"frameworks-to-obligations"},"title":"Frameworks, commitments and legal obligations, 2023–2026","claimIds":[]},{"target":{"kind":"reading"},"title":"Founding and early leadership","claimIds":[]}]},"version":"131evrz"}