{"id":"W4388824487","doi":"10.1038/s41562-023-01710-w","title":"The Turing test is not a good benchmark for thought in LLMs","year":2023,"lang":"en","type":"letter","venue":"Nature Human Behaviour","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Test (biology); Turing test; Benchmark (surveying); Psychology; Computer science; Artificial intelligence; Biology; Geography; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00124586,0.0007693509,0.0007153061,0.0004324919,0.0007365234,0.0009609442,0.00518819,0.002441983,0.00002031007],"category_scores_gemma":[0.0002777519,0.0006015822,0.0005364433,0.0009425288,0.0001452606,0.0002661204,0.001525695,0.007631432,0.00005016143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004264186,"about_ca_system_score_gemma":0.0001767999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009506477,"about_ca_topic_score_gemma":0.0004383746,"domain_scores_codex":[0.9947163,0.0001523295,0.0008156543,0.001830262,0.001181813,0.001303675],"domain_scores_gemma":[0.9946941,0.002067477,0.0003896948,0.002457492,0.0002922446,0.00009905664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003580042,0.000121538,0.003758593,0.0001132905,0.00002772017,0.0004722571,0.000527024,0.000005640124,0.00002981879,0.001451676,0.9884936,0.004995264],"study_design_scores_gemma":[0.001251716,0.0003933498,0.0866088,0.0003156326,0.0001030686,0.00008398651,0.00002762598,0.002261976,0.0004819468,0.01565862,0.8909265,0.001886819],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.007204644,0.001692716,0.003227696,0.9653037,0.01328632,0.005285988,0.0006177662,0.001882018,0.001499218],"genre_scores_gemma":[0.08991196,0.00009032877,0.04252754,0.7714416,0.03176059,0.002986774,0.001078356,0.0008464362,0.05935642],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.193862,"threshold_uncertainty_score":0.9996436,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02567321357612041,"score_gpt":0.2997814718697058,"score_spread":0.2741082582935854,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}