{"id":"53aec1bad179ad357c86e54af42ae17a54676e93d83893e37f333539469d5507","title":"Ajeya Cotra argues alignment is not the same as making AI good","argument":"Ajeya Cotra’s article, published March 26, 2023, argues that “alignment” should describe whether AI systems try to do what their designers want, not whether their actions are good for the world. She says this narrower framing could help researchers identify technical problems for experiments, code, and proofs to address, while leaving decisions about what counts as good to society and its institutions.\n\nCotra’s examples distinguish alignment from broader risks: systems could faithfully serve harmful users, contribute to inequality, make high-stakes errors, or be affected by security failures. She also points to questions about who has authority to direct AI and how systems should handle conflicting preferences. In her view, alignment research may reduce some dangers, but it cannot resolve all the political, social, and moral questions involved in building a flourishing future. She expects different intellectual communities to address different parts of that work.\n\nThe article’s examples describe possible outcomes, not reported events. It leaves open how researchers could develop and evaluate techniques that make powerful AI systems reliably try to follow their designers’ intent, and how society should decide whose intent those systems should serve.","topicIds":["work-and-business--jobs-and-occupations","job-displacement-and-creation"],"domain":"other","claimType":"attributed reading","limits":"Text as retrieved on October 29, 2026; originally published March 26, 2023. Cotra presents misuse, inequality, errors, and other harms as possible scenarios, not as events shown to have occurred. The article does not specify methods or evaluation results for determining whether powerful AI systems will follow their designers’ intent.","speaker":{"name":"Ajeya Cotra","roleAtSource":"Publisher"},"source":{"title":"\"Aligned\" shouldn't be a synonym for \"good\"","publisher":"Ajeya Cotra","format":"Article","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","publishedAt":"2023-03-26T18:04:05+00:00","dateBasis":"Date stated on the publisher’s page."},"evidence":[{"text":"Cotra defines alignment as developing AI systems that try to do what their designers want.","excerpt":"they’re always “trying their best” to do what their designers want them to do","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"},{"text":"Cotra argues that alignment, as she defines it, is not sufficient to ensure AI is good for the world.","excerpt":"Perfect alignment techniques just mean that AI systems won’t want to deliberately disregard the desires of whatever humans designed and trained them.","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"},{"text":"Cotra lists misuse, inequality, high-stakes errors, security, global stability, preference aggregation, and philosophical questions as concerns that alignment alone may not resolve.","excerpt":"Potentially important issues this would not necessarily solve:","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"},{"text":"Cotra argues that decisions about what counts as good for the world should not be left to AI researchers working on alignment alone.","excerpt":"I don’t think it’s their place to make that decision on society’s behalf.","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.planned-obsolescence.org/p/aligned-vs-good","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"What methods could establish whether powerful AI systems reliably try to follow their designers’ intent, and whose intent should they follow when people disagree?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Ajeya Cotra argues alignment is not the same as making AI good","summary":"Ajeya Cotra’s article, published March 26, 2023, argues that “alignment” should describe whether AI systems try to do what their designers want, not whether their actions are good for the world. She says this narrower framing could help researchers identify technical problems for experiments, code, and proofs to address, while leaving decisions about what counts as good to society and its institutions.\n\nCotra’s examples distinguish alignment from broader risks: systems could faithfully serve harmful users, contribute to inequality, make high-stakes errors, or be affected by security failures. She also points to questions about who has authority to direct AI and how systems should handle conflicting preferences. In her view, alignment research may reduce some dangers, but it cannot resolve all the political, social, and moral questions involved in building a flourishing future. She expects different intellectual communities to address different parts of that work.\n\nThe article’s examples describe possible outcomes, not reported events. It leaves open how researchers could develop and evaluate techniques that make powerful AI systems reliably try to follow their designers’ intent, and how society should decide whose intent those systems should serve.","question":"What methods could establish whether powerful AI systems reliably try to follow their designers’ intent, and whose intent should they follow when people disagree?","claims":[{"text":"Cotra defines alignment as developing AI systems that try to do what their designers want.","excerpt":"they’re always “trying their best” to do what their designers want them to do","support":"source-stated"},{"text":"Cotra argues that alignment, as she defines it, is not sufficient to ensure AI is good for the world.","excerpt":"Perfect alignment techniques just mean that AI systems won’t want to deliberately disregard the desires of whatever humans designed and trained them.","support":"source-stated"},{"text":"Cotra lists misuse, inequality, high-stakes errors, security, global stability, preference aggregation, and philosophical questions as concerns that alignment alone may not resolve.","excerpt":"Potentially important issues this would not necessarily solve:","support":"source-stated"},{"text":"Cotra argues that decisions about what counts as good for the world should not be left to AI researchers working on alignment alone.","excerpt":"I don’t think it’s their place to make that decision on society’s behalf.","support":"source-stated"}],"limitations":["Text as retrieved on October 29, 2026; originally published March 26, 2023.","Cotra presents misuse, inequality, errors, and other harms as possible scenarios, not as events shown to have occurred.","The article does not specify methods or evaluation results for determining whether powerful AI systems will follow their designers’ intent."],"mediaId":null,"correctionReason":null,"id":"53aec1bad179ad357c86e54af42ae17a54676e93d83893e37f333539469d5507","publicationId":"4c0f7bfc-6d45-1133-c9fe-3cf9f2cae0c2","version":1,"sourceUrl":"https://www.planned-obsolescence.org/p/aligned-vs-good","sourceTitle":"\"Aligned\" shouldn't be a synonym for \"good\"","publisher":"Ajeya Cotra","publishedAt":"2023-03-26T18:04:05+00:00","originalPublished":{"value":"2023-03-26T18:04:05+00:00","precision":"instant","basis":"backfill:article_published"},"firstObservedAt":"2026-10-29T00:46:03.475Z","createdAt":"2026-10-29T15:59:56.906Z","historical":true,"entityIds":[],"topicIds":["work-and-business--jobs-and-occupations","job-displacement-and-creation"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.planned-obsolescence.org/p/aligned-vs-good","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"cd48dd095882418d226de9af035b9978f2f4a42921c691aa9b8a92ab889a4013","rubricVersion":"unrecorded","provider":"anthropic","model":"claude-opus-5-5","reasonCodes":["bridge_admitted_by_model","second_opinion_categorical"],"confidence":1,"decidedAt":"2026-10-29T00:46:00.891Z"},"provenance":{"textHash":"c56dd3a36063191645ac692acf3e4e2c5e80a18ad6026108320dae44b5899fdd","observationId":"3c36d439ad3112d7bd0ae9b0baf8a727144df531913bd606247ab05769715776","retrievedAt":"2026-10-29T00:47:37.967Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"6e766b9f-4469-7589-a701-242344b83d4c"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"08b72813-c739-b9dc-8f5c-9fdeee0579ef"}},"audit":{"status":"passed","reviewedAt":"2026-10-29T15:58:45.454Z","model":"anthropic/claude-opus-5.5"}},"canonicalUrl":"https://escapemeridian.com/readings/ajeya-cotra-argues-alignment-is-not-the-same-as-making-ai-good-53aec1ba","formats":{"html":"/readings/ajeya-cotra-argues-alignment-is-not-the-same-as-making-ai-good-53aec1ba","markdown":"/readings/ajeya-cotra-argues-alignment-is-not-the-same-as-making-ai-good-53aec1ba.md","json":"/readings/ajeya-cotra-argues-alignment-is-not-the-same-as-making-ai-good-53aec1ba.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-ai-alignment","name":"AI alignment","explanation":"Research and practice aimed at making AI systems pursue the goals their builders and users intend.","referenceUrl":"https://en.wikipedia.org/wiki/AI_alignment"}],"entities":[]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"53aec1bad179ad357c86e54af42ae17a54676e93d83893e37f333539469d5507","revision":"4c0f7bfc-6d45-1133-c9fe-3cf9f2cae0c2","revisionKind":"publication-id","title":"Ajeya Cotra argues alignment is not the same as making AI good","url":"https://escapemeridian.com/readings/ajeya-cotra-argues-alignment-is-not-the-same-as-making-ai-good-53aec1ba"},"source":{"type":"source","id":"https://www.planned-obsolescence.org/p/aligned-vs-good","revision":"c56dd3a36063191645ac692acf3e4e2c5e80a18ad6026108320dae44b5899fdd","revisionKind":"sha256-source-text","title":"\"Aligned\" shouldn't be a synonym for \"good\"","url":"https://www.planned-obsolescence.org/p/aligned-vs-good"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"53aec1bad179ad357c86e54af42ae17a54676e93d83893e37f333539469d5507","title":"Ajeya Cotra argues alignment is not the same as making AI good","argument":"Ajeya Cotra’s article, published March 26, 2023, argues that “alignment” should describe whether AI systems try to do what their designers want, not whether their actions are good for the world. She says this narrower framing could help researchers identify technical problems for experiments, code, and proofs to address, while leaving decisions about what counts as good to society and its institutions.\n\nCotra’s examples distinguish alignment from broader risks: systems could faithfully serve harmful users, contribute to inequality, make high-stakes errors, or be affected by security failures. She also points to questions about who has authority to direct AI and how systems should handle conflicting preferences. In her view, alignment research may reduce some dangers, but it cannot resolve all the political, social, and moral questions involved in building a flourishing future. She expects different intellectual communities to address different parts of that work.\n\nThe article’s examples describe possible outcomes, not reported events. It leaves open how researchers could develop and evaluate techniques that make powerful AI systems reliably try to follow their designers’ intent, and how society should decide whose intent those systems should serve.","topicIds":["work-and-business--jobs-and-occupations","job-displacement-and-creation"],"domain":"other","claimType":"attributed reading","limits":"Text as retrieved on October 29, 2026; originally published March 26, 2023. Cotra presents misuse, inequality, errors, and other harms as possible scenarios, not as events shown to have occurred. The article does not specify methods or evaluation results for determining whether powerful AI systems will follow their designers’ intent.","speaker":{"name":"Ajeya Cotra","roleAtSource":"Publisher"},"source":{"title":"\"Aligned\" shouldn't be a synonym for \"good\"","publisher":"Ajeya Cotra","format":"Article","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","publishedAt":"2023-03-26T18:04:05+00:00","dateBasis":"Date stated on the publisher’s page."},"evidence":[{"text":"Cotra defines alignment as developing AI systems that try to do what their designers want.","excerpt":"they’re always “trying their best” to do what their designers want them to do","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"},{"text":"Cotra argues that alignment, as she defines it, is not sufficient to ensure AI is good for the world.","excerpt":"Perfect alignment techniques just mean that AI systems won’t want to deliberately disregard the desires of whatever humans designed and trained them.","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"},{"text":"Cotra lists misuse, inequality, high-stakes errors, security, global stability, preference aggregation, and philosophical questions as concerns that alignment alone may not resolve.","excerpt":"Potentially important issues this would not necessarily solve:","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"},{"text":"Cotra argues that decisions about what counts as good for the world should not be left to AI researchers working on alignment alone.","excerpt":"I don’t think it’s their place to make that decision on society’s behalf.","url":"https://www.planned-obsolescence.org/p/aligned-vs-good","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.planned-obsolescence.org/p/aligned-vs-good","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"What methods could establish whether powerful AI systems reliably try to follow their designers’ intent, and whose intent should they follow when people disagree?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Ajeya Cotra argues alignment is not the same as making AI good","summary":"Ajeya Cotra’s article, published March 26, 2023, argues that “alignment” should describe whether AI systems try to do what their designers want, not whether their actions are good for the world. She says this narrower framing could help researchers identify technical problems for experiments, code, and proofs to address, while leaving decisions about what counts as good to society and its institutions.\n\nCotra’s examples distinguish alignment from broader risks: systems could faithfully serve harmful users, contribute to inequality, make high-stakes errors, or be affected by security failures. She also points to questions about who has authority to direct AI and how systems should handle conflicting preferences. In her view, alignment research may reduce some dangers, but it cannot resolve all the political, social, and moral questions involved in building a flourishing future. She expects different intellectual communities to address different parts of that work.\n\nThe article’s examples describe possible outcomes, not reported events. It leaves open how researchers could develop and evaluate techniques that make powerful AI systems reliably try to follow their designers’ intent, and how society should decide whose intent those systems should serve.","question":"What methods could establish whether powerful AI systems reliably try to follow their designers’ intent, and whose intent should they follow when people disagree?","claims":[{"text":"Cotra defines alignment as developing AI systems that try to do what their designers want.","excerpt":"they’re always “trying their best” to do what their designers want them to do","support":"source-stated"},{"text":"Cotra argues that alignment, as she defines it, is not sufficient to ensure AI is good for the world.","excerpt":"Perfect alignment techniques just mean that AI systems won’t want to deliberately disregard the desires of whatever humans designed and trained them.","support":"source-stated"},{"text":"Cotra lists misuse, inequality, high-stakes errors, security, global stability, preference aggregation, and philosophical questions as concerns that alignment alone may not resolve.","excerpt":"Potentially important issues this would not necessarily solve:","support":"source-stated"},{"text":"Cotra argues that decisions about what counts as good for the world should not be left to AI researchers working on alignment alone.","excerpt":"I don’t think it’s their place to make that decision on society’s behalf.","support":"source-stated"}],"limitations":["Text as retrieved on October 29, 2026; originally published March 26, 2023.","Cotra presents misuse, inequality, errors, and other harms as possible scenarios, not as events shown to have occurred.","The article does not specify methods or evaluation results for determining whether powerful AI systems will follow their designers’ intent."],"mediaId":null,"correctionReason":null,"id":"53aec1bad179ad357c86e54af42ae17a54676e93d83893e37f333539469d5507","publicationId":"4c0f7bfc-6d45-1133-c9fe-3cf9f2cae0c2","version":1,"sourceUrl":"https://www.planned-obsolescence.org/p/aligned-vs-good","sourceTitle":"\"Aligned\" shouldn't be a synonym for \"good\"","publisher":"Ajeya Cotra","publishedAt":"2023-03-26T18:04:05+00:00","originalPublished":{"value":"2023-03-26T18:04:05+00:00","precision":"instant","basis":"backfill:article_published"},"firstObservedAt":"2026-10-29T00:46:03.475Z","createdAt":"2026-10-29T15:59:56.906Z","historical":true,"entityIds":[],"topicIds":["work-and-business--jobs-and-occupations","job-displacement-and-creation"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.planned-obsolescence.org/p/aligned-vs-good","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"cd48dd095882418d226de9af035b9978f2f4a42921c691aa9b8a92ab889a4013","rubricVersion":"unrecorded","provider":"anthropic","model":"claude-opus-5-5","reasonCodes":["bridge_admitted_by_model","second_opinion_categorical"],"confidence":1,"decidedAt":"2026-10-29T00:46:00.891Z"},"provenance":{"textHash":"c56dd3a36063191645ac692acf3e4e2c5e80a18ad6026108320dae44b5899fdd","observationId":"3c36d439ad3112d7bd0ae9b0baf8a727144df531913bd606247ab05769715776","retrievedAt":"2026-10-29T00:47:37.967Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"6e766b9f-4469-7589-a701-242344b83d4c"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"08b72813-c739-b9dc-8f5c-9fdeee0579ef"}},"audit":{"status":"passed","reviewedAt":"2026-10-29T15:58:45.454Z","model":"anthropic/claude-opus-5.5"}}}],"audits":[{"publicationId":"4c0f7bfc-6d45-1133-c9fe-3cf9f2cae0c2","verdict":"passed","findings":[{"dimension":"attribution","status":"pass","explanation":"The article is correctly attributed to Ajeya Cotra, who is named as the author and publisher, and its arguments are consistently presented as hers.","excerpt":"That’s what I mean when I talk about alignment."},{"dimension":"summary","status":"pass","explanation":"The title, summary and question match the article's thesis: alignment means AI trying to do what its designers want, which is narrower than being good for the world. The summary explains the term in plain language, lists her example risks, and conveys her view that deciding what is good belongs to society and different communities. It is understandable without specialist background.","excerpt":"developing perfect alignment techniques is obviously not enough to ensure that AI is good for the world"},{"dimension":"date","status":"pass","explanation":"The draft gives March 26, 2023, the UTC calendar day of the originalPublished instant, at day precision, and it matches the source dateline. The page is a publisher page, so no archive disclosure is required. The modification date equals the publication date. The draft uses no hindsight framing.","excerpt":"Ajeya Cotra\nMar 26, 2023"},{"dimension":"support","status":"pass","explanation":"Each claim is directly supported by the quoted source text. The limitations correctly describe her scenarios as hypothetical. The question about whose intent AI should follow is grounded in her preference-aggregation and chain-of-command points, and the draft does not invent stakeholder claims.","excerpt":"I don’t think it’s their place to make that decision on society’s behalf."},{"dimension":"media","status":"pass","explanation":"No media was selected and none was supplied, so there is no media identity or relevance issue.","excerpt":null}],"createdAt":"2026-10-29T15:58:45.454Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}