{"id":"8b4f8b57faf003bfdecd79b4970071f6c75f4a5ca57d2f20e3331a89b8e8e232","title":"Pew Research Center reports model choice reshapes synthetic polling results","argument":"Pew Research Center’s report, published September 30, 2026, compares AI-generated survey responses with human poll results and examines how results vary by model. The Center used GPT-5.1 and Claude Opus 4.6 to simulate people from its American Trends Panel, using the same questionnaire and respondent profiles. It reports that neither model reproduced the human panel especially well, and that the models often produced sharply different pictures of public opinion. For example, GPT tended to favor extreme answers, while Opus tended to favor middle options; the report says this pattern appeared across questions on different topics. The difference is more than a matter of which model has the lower average error: choosing a model can change the story a synthetic poll tells about issues and groups. That matters because readers of such polls may encounter incompatible depictions of public attitudes even when the synthetic samples are built in the same way. The Center says newer models and changes to synthetic sample construction could reduce errors or alter these patterns. Its findings concern this experiment, including selected panelists and surveys, and do not address other uses of AI models in polling. How would these results change with other models, respondent profiles or survey questions?","topicIds":["artificial-general-intelligence"],"domain":"other","claimType":"attributed reading","limits":"Text as retrieved on October 30, 2026; originally published September 30, 2026. The analysis compares two models using a particular set of panelist profiles and surveys; the report says newer models or changes to synthetic sample construction could produce different results. The report says its study does not address other uses of AI models in polling.","speaker":{"name":"Pew Research Center","roleAtSource":"Publisher"},"source":{"title":"How synthetic polling results change based on the AI model","publisher":"Pew Research Center","format":"Article","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","publishedAt":"2026-09-30T17:55:21.000Z","dateBasis":"Date supplied by the publisher’s feed."},"evidence":[{"text":"Pew Research Center reports that neither tested model replicated the human panel results especially well on average.","excerpt":"Opus performed slightly better, with an average absolute error of 11.4 percentage points (compared with 13.3 percentage points for GPT).","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"Pew Research Center says the synthetic samples produced substantially different pictures of public opinion, and neither reflected actual opinion overall.","excerpt":"each synthetic sample painted a very different picture of the American public on multiple dimensions, and neither truly reflected actual public opinion.","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"Pew Research Center reports a recurring difference in response style: GPT leaned toward extreme choices, while Opus leaned toward middle choices.","excerpt":"GPT tended to favor response options at the far ends of scales, such as “extremely” or “not at all.” By contrast, Opus tended to favor “middle” options","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"Pew Research Center says model choice alone can produce large, systematic differences between synthetic samples built in the same way.","excerpt":"the choice of model alone is enough to yield large, systematic differences between synthetic samples that were otherwise built in exactly the same way.","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"The report was published on September 30, 2026.","excerpt":"Report\n|\nSeptember 30, 2026\nCan AI Stand In for Human Survey-Takers? Not Really","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How would these results change with other models, respondent profiles or survey questions?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Pew Research Center reports model choice reshapes synthetic polling results","summary":"Pew Research Center’s report, published September 30, 2026, compares AI-generated survey responses with human poll results and examines how results vary by model. The Center used GPT-5.1 and Claude Opus 4.6 to simulate people from its American Trends Panel, using the same questionnaire and respondent profiles. It reports that neither model reproduced the human panel especially well, and that the models often produced sharply different pictures of public opinion. For example, GPT tended to favor extreme answers, while Opus tended to favor middle options; the report says this pattern appeared across questions on different topics. The difference is more than a matter of which model has the lower average error: choosing a model can change the story a synthetic poll tells about issues and groups. That matters because readers of such polls may encounter incompatible depictions of public attitudes even when the synthetic samples are built in the same way. The Center says newer models and changes to synthetic sample construction could reduce errors or alter these patterns. Its findings concern this experiment, including selected panelists and surveys, and do not address other uses of AI models in polling. How would these results change with other models, respondent profiles or survey questions?","question":"How would these results change with other models, respondent profiles or survey questions?","claims":[{"text":"Pew Research Center reports that neither tested model replicated the human panel results especially well on average.","excerpt":"Opus performed slightly better, with an average absolute error of 11.4 percentage points (compared with 13.3 percentage points for GPT).","support":"source-stated"},{"text":"Pew Research Center says the synthetic samples produced substantially different pictures of public opinion, and neither reflected actual opinion overall.","excerpt":"each synthetic sample painted a very different picture of the American public on multiple dimensions, and neither truly reflected actual public opinion.","support":"source-stated"},{"text":"Pew Research Center reports a recurring difference in response style: GPT leaned toward extreme choices, while Opus leaned toward middle choices.","excerpt":"GPT tended to favor response options at the far ends of scales, such as “extremely” or “not at all.” By contrast, Opus tended to favor “middle” options","support":"source-stated"},{"text":"Pew Research Center says model choice alone can produce large, systematic differences between synthetic samples built in the same way.","excerpt":"the choice of model alone is enough to yield large, systematic differences between synthetic samples that were otherwise built in exactly the same way.","support":"source-stated"},{"text":"The report was published on September 30, 2026.","excerpt":"Report\n|\nSeptember 30, 2026\nCan AI Stand In for Human Survey-Takers? Not Really","support":"source-stated"}],"limitations":["Text as retrieved on October 30, 2026; originally published September 30, 2026.","The analysis compares two models using a particular set of panelist profiles and surveys; the report says newer models or changes to synthetic sample construction could produce different results.","The report says its study does not address other uses of AI models in polling."],"mediaId":null,"correctionReason":null,"id":"8b4f8b57faf003bfdecd79b4970071f6c75f4a5ca57d2f20e3331a89b8e8e232","publicationId":"9b903ec1-c646-4563-9ef9-76e7205e20dc","version":1,"sourceUrl":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","sourceTitle":"How synthetic polling results change based on the AI model","publisher":"Pew Research Center","publishedAt":"2026-09-30T17:55:21.000Z","originalPublished":{"value":"2026-09-30T17:55:21.000Z","precision":"instant","basis":"backfill:feed_published"},"firstObservedAt":"2026-10-18T03:39:24.989Z","createdAt":"2026-11-05T09:58:23.020Z","historical":true,"entityIds":["pew-research-center"],"topicIds":["artificial-general-intelligence"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"add57bfc4800f8d730f615f18a8370b5f27eb1d32b228ba713ab6c16b55ab585","rubricVersion":"em-backfill-context/3","provider":"typesafe","model":"jev-1.13.0","reasonCodes":["bridge_admitted_by_model"],"confidence":0.52,"decidedAt":"2026-10-30T04:33:56.335Z"},"provenance":{"textHash":"7ece0e991bcb7f3cc522a5c6e378a8b53cd264eaa73f0ae2a3a6ca254dc43de5","observationId":"8e012886080b5feebc74646401c2907bcf2ef06da72383f1c3a71b86310e9215","retrievedAt":"2026-10-30T04:35:47.769Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"34a0896a-cd39-33b6-8565-6785e30e3544"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"2fb1cef0-5f99-c2df-f6a3-bd52a3280f7d"}},"audit":{"status":"passed","reviewedAt":"2026-11-05T09:53:45.032Z","model":"anthropic/claude-opus-5.5"}},"canonicalUrl":"https://escapemeridian.com/readings/pew-research-center-reports-model-choice-reshapes-synthetic-8b4f8b57","formats":{"html":"/readings/pew-research-center-reports-model-choice-reshapes-synthetic-8b4f8b57","markdown":"/readings/pew-research-center-reports-model-choice-reshapes-synthetic-8b4f8b57.md","json":"/readings/pew-research-center-reports-model-choice-reshapes-synthetic-8b4f8b57.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.","maintainedGuideLinks":[],"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":[],"entities":[{"id":"pew-research-center","name":"Pew Research Center","kind":"organization","context":"Pew Research Center studies public attitudes and social change through surveys and other empirical research.","referenceUrls":["https://www.pewresearch.org/","https://www.pewresearch.org/internet/2025/04/03/how-the-us-public-and-ai-experts-view-artificial-intelligence/"],"path":"/entities/pew-research-center","json":"/entities/pew-research-center.json","markdown":"/entities/pew-research-center.md"},{"id":"claude","name":"Claude","kind":"model","context":"Claude is Anthropic’s family of AI models and assistants for tasks such as writing, analysis and coding.","referenceUrls":["https://claude.com/product/overview","https://www.anthropic.com/news","https://www.anthropic.com/research/team/economics"],"path":"/entities/claude","json":"/entities/claude.json","markdown":"/entities/claude.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"8b4f8b57faf003bfdecd79b4970071f6c75f4a5ca57d2f20e3331a89b8e8e232","revision":"9b903ec1-c646-4563-9ef9-76e7205e20dc","revisionKind":"publication-id","title":"Pew Research Center reports model choice reshapes synthetic polling results","url":"https://escapemeridian.com/readings/pew-research-center-reports-model-choice-reshapes-synthetic-8b4f8b57"},"source":{"type":"source","id":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","revision":"7ece0e991bcb7f3cc522a5c6e378a8b53cd264eaa73f0ae2a3a6ca254dc43de5","revisionKind":"sha256-source-text","title":"How synthetic polling results change based on the AI model","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/"},"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":"8b4f8b57faf003bfdecd79b4970071f6c75f4a5ca57d2f20e3331a89b8e8e232","title":"Pew Research Center reports model choice reshapes synthetic polling results","argument":"Pew Research Center’s report, published September 30, 2026, compares AI-generated survey responses with human poll results and examines how results vary by model. The Center used GPT-5.1 and Claude Opus 4.6 to simulate people from its American Trends Panel, using the same questionnaire and respondent profiles. It reports that neither model reproduced the human panel especially well, and that the models often produced sharply different pictures of public opinion. For example, GPT tended to favor extreme answers, while Opus tended to favor middle options; the report says this pattern appeared across questions on different topics. The difference is more than a matter of which model has the lower average error: choosing a model can change the story a synthetic poll tells about issues and groups. That matters because readers of such polls may encounter incompatible depictions of public attitudes even when the synthetic samples are built in the same way. The Center says newer models and changes to synthetic sample construction could reduce errors or alter these patterns. Its findings concern this experiment, including selected panelists and surveys, and do not address other uses of AI models in polling. How would these results change with other models, respondent profiles or survey questions?","topicIds":["artificial-general-intelligence"],"domain":"other","claimType":"attributed reading","limits":"Text as retrieved on October 30, 2026; originally published September 30, 2026. The analysis compares two models using a particular set of panelist profiles and surveys; the report says newer models or changes to synthetic sample construction could produce different results. The report says its study does not address other uses of AI models in polling.","speaker":{"name":"Pew Research Center","roleAtSource":"Publisher"},"source":{"title":"How synthetic polling results change based on the AI model","publisher":"Pew Research Center","format":"Article","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","publishedAt":"2026-09-30T17:55:21.000Z","dateBasis":"Date supplied by the publisher’s feed."},"evidence":[{"text":"Pew Research Center reports that neither tested model replicated the human panel results especially well on average.","excerpt":"Opus performed slightly better, with an average absolute error of 11.4 percentage points (compared with 13.3 percentage points for GPT).","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"Pew Research Center says the synthetic samples produced substantially different pictures of public opinion, and neither reflected actual opinion overall.","excerpt":"each synthetic sample painted a very different picture of the American public on multiple dimensions, and neither truly reflected actual public opinion.","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"Pew Research Center reports a recurring difference in response style: GPT leaned toward extreme choices, while Opus leaned toward middle choices.","excerpt":"GPT tended to favor response options at the far ends of scales, such as “extremely” or “not at all.” By contrast, Opus tended to favor “middle” options","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"Pew Research Center says model choice alone can produce large, systematic differences between synthetic samples built in the same way.","excerpt":"the choice of model alone is enough to yield large, systematic differences between synthetic samples that were otherwise built in exactly the same way.","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"},{"text":"The report was published on September 30, 2026.","excerpt":"Report\n|\nSeptember 30, 2026\nCan AI Stand In for Human Survey-Takers? Not Really","url":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How would these results change with other models, respondent profiles or survey questions?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Pew Research Center reports model choice reshapes synthetic polling results","summary":"Pew Research Center’s report, published September 30, 2026, compares AI-generated survey responses with human poll results and examines how results vary by model. The Center used GPT-5.1 and Claude Opus 4.6 to simulate people from its American Trends Panel, using the same questionnaire and respondent profiles. It reports that neither model reproduced the human panel especially well, and that the models often produced sharply different pictures of public opinion. For example, GPT tended to favor extreme answers, while Opus tended to favor middle options; the report says this pattern appeared across questions on different topics. The difference is more than a matter of which model has the lower average error: choosing a model can change the story a synthetic poll tells about issues and groups. That matters because readers of such polls may encounter incompatible depictions of public attitudes even when the synthetic samples are built in the same way. The Center says newer models and changes to synthetic sample construction could reduce errors or alter these patterns. Its findings concern this experiment, including selected panelists and surveys, and do not address other uses of AI models in polling. How would these results change with other models, respondent profiles or survey questions?","question":"How would these results change with other models, respondent profiles or survey questions?","claims":[{"text":"Pew Research Center reports that neither tested model replicated the human panel results especially well on average.","excerpt":"Opus performed slightly better, with an average absolute error of 11.4 percentage points (compared with 13.3 percentage points for GPT).","support":"source-stated"},{"text":"Pew Research Center says the synthetic samples produced substantially different pictures of public opinion, and neither reflected actual opinion overall.","excerpt":"each synthetic sample painted a very different picture of the American public on multiple dimensions, and neither truly reflected actual public opinion.","support":"source-stated"},{"text":"Pew Research Center reports a recurring difference in response style: GPT leaned toward extreme choices, while Opus leaned toward middle choices.","excerpt":"GPT tended to favor response options at the far ends of scales, such as “extremely” or “not at all.” By contrast, Opus tended to favor “middle” options","support":"source-stated"},{"text":"Pew Research Center says model choice alone can produce large, systematic differences between synthetic samples built in the same way.","excerpt":"the choice of model alone is enough to yield large, systematic differences between synthetic samples that were otherwise built in exactly the same way.","support":"source-stated"},{"text":"The report was published on September 30, 2026.","excerpt":"Report\n|\nSeptember 30, 2026\nCan AI Stand In for Human Survey-Takers? Not Really","support":"source-stated"}],"limitations":["Text as retrieved on October 30, 2026; originally published September 30, 2026.","The analysis compares two models using a particular set of panelist profiles and surveys; the report says newer models or changes to synthetic sample construction could produce different results.","The report says its study does not address other uses of AI models in polling."],"mediaId":null,"correctionReason":null,"id":"8b4f8b57faf003bfdecd79b4970071f6c75f4a5ca57d2f20e3331a89b8e8e232","publicationId":"9b903ec1-c646-4563-9ef9-76e7205e20dc","version":1,"sourceUrl":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","sourceTitle":"How synthetic polling results change based on the AI model","publisher":"Pew Research Center","publishedAt":"2026-09-30T17:55:21.000Z","originalPublished":{"value":"2026-09-30T17:55:21.000Z","precision":"instant","basis":"backfill:feed_published"},"firstObservedAt":"2026-10-18T03:39:24.989Z","createdAt":"2026-11-05T09:58:23.020Z","historical":true,"entityIds":["pew-research-center"],"topicIds":["artificial-general-intelligence"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://www.pewresearch.org/data-labs/2026/09/30/how-synthetic-polling-results-change-based-on-the-ai-model/","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"add57bfc4800f8d730f615f18a8370b5f27eb1d32b228ba713ab6c16b55ab585","rubricVersion":"em-backfill-context/3","provider":"typesafe","model":"jev-1.13.0","reasonCodes":["bridge_admitted_by_model"],"confidence":0.52,"decidedAt":"2026-10-30T04:33:56.335Z"},"provenance":{"textHash":"7ece0e991bcb7f3cc522a5c6e378a8b53cd264eaa73f0ae2a3a6ca254dc43de5","observationId":"8e012886080b5feebc74646401c2907bcf2ef06da72383f1c3a71b86310e9215","retrievedAt":"2026-10-30T04:35:47.769Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"34a0896a-cd39-33b6-8565-6785e30e3544"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"2fb1cef0-5f99-c2df-f6a3-bd52a3280f7d"}},"audit":{"status":"passed","reviewedAt":"2026-11-05T09:53:45.032Z","model":"anthropic/claude-opus-5.5"}}}],"audits":[{"publicationId":"9b903ec1-c646-4563-9ef9-76e7205e20dc","verdict":"passed","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading attributes the findings to Pew Research Center, which matches the page's publisher and author byline. The page is one chapter of a single report with its own analysis, not a listing of other pieces. Claims are consistently framed as what Pew reports or says.","excerpt":"By Athena Chapekis, Arnold Lau, Samuel Bestvater, Sono Shah, Andrew Mercer and Aaron Smith"},{"dimension":"summary","status":"pass","explanation":"The reading leads with the actor, Pew, and plainly explains synthetic polling as AI-generated survey responses that simulate panel members. It identifies the two models and preserves the core thesis: model choice can change the story a synthetic poll tells. It accurately conveys the extreme-versus-middle response pattern and Pew's caveats. The question follows from the stated limits. The American Trends Panel is lightly explained but understandable from context. Minor gap: the page is one chapter of the larger report, but this does not mislead.","excerpt":"Here, the choice of model alone has the potential to reshape the narrative around public opinion of abortion."},{"dimension":"date","status":"pass","explanation":"The originalPublished instant, 2026-09-30, matches the page dateline of September 30, 2026, and the reading states the date at day precision. The page is a publisher page, so no archive disclosure is needed. modifiedAt equals the publication time. The reading makes no hindsight claims and presents the possibility of future model improvements as Pew's conditional statement, not as an outcome.","excerpt":"September 30, 2026"},{"dimension":"support","status":"pass","explanation":"Each claim matches the source: the error figures (11.4 vs 13.3 points); the very different pictures of public opinion; GPT favoring extreme options and Opus favoring middle ones regardless of topic; and model choice alone producing systematic differences. The inference about readers encountering incompatible depictions follows directly from Pew's own narrative framing. The caveats about newer models and scope are source-stated.","excerpt":"This was broadly true regardless of what the scale was or what the question was about."},{"dimension":"media","status":"pass","explanation":"No media was selected, and no verified media candidates were supplied. The source page's media status is unchecked with no items, so omitting media is appropriate.","excerpt":null}],"createdAt":"2026-11-05T09:53:45.032Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}