Knowledge

Roman Yampolskiy

Source πŸ“

65: 1350: 222:, and has advocated research into "boxing" artificial intelligence. More broadly, Yampolskiy and his collaborator, MichaΓ«l Trazzi, have proposed introducing "Achilles' heels" into potentially dangerous AI, for example by barring an AI from accessing and modifying its own source code. Another proposal is to apply a "security mindset" to AI safety, itemizing potential outcomes in order to better evaluate proposed safety mechanisms. 272:, a new field of study founded to analyze the forms and limits of intelligence. Yampolskiy considers AI to be a sub-field of this. An example of Yampolskiy's intellectology work is an attempt to determine the relation between various types of minds and the accessible 889:
Roman V. Yampolskiy. Turing Test as a Defining Feature of AI-Completeness. In Artificial Intelligence, Evolutionary Computation and Metaheuristics (AIECM) --In the footsteps of Alan Turing. Xin-She Yang (Ed.). pp. 3–17. (Chapter 1). Springer, London. 2013.
229:
and has proposed pausing AI development, arguing that "Imagining humans can control superintelligent AI is a little like imagining that an ant can control the outcome of an NFL football game being played around it". He joined AI researchers such as
807: 967: 1353: 678: 960: 1317: 953: 219: 1034: 976: 829: 1105: 894: 1145: 591: 626: 729: 1140: 937: 1324: 1304: 615:
Trazzi, MichaΓ«l, and Roman V. Yampolskiy. "Building safer AGI by introducing artificial stupidity." arXiv preprint arXiv:1808.03644 (2018).
203:(2008). He is currently the director of Cyber Security Laboratory in the department of Computer Engineering and Computer Science at the 239: 542: 1110: 249:
podcast in 2024, Yampolskiy predicted the chance that AI could lead to human extinction at "99.9% within the next hundred years".
1150: 383: 253: 867:
3rd Annual Global Online Conference on Information and Computer Technology (GOCICT16). Louisville, KY, USA. 16–18 November 2016
1387: 1382: 1292: 791: 679:"AI Superintelligence Alert: Expert Warns of Uncontrollable Risks, Calling It a Potential 'An Existential Catastrophe'" 361: 348: 843: 1029: 651: 335: 322: 309: 1039: 994: 455: 430: 1100: 22: 1331: 1191: 1120: 1337: 891: 204: 153: 925: 1090: 1074: 1024: 1125: 1044: 865:
Ziesche, Soenke; Yampolskiy, Roman V. (2016). "Artificial Fun: Mapping Minds to the Space of Fun".
703: 521: 180: 148: 980: 945: 1377: 1049: 388: 1004: 200: 118: 1372: 1095: 8: 1310: 754: 257: 870: 478:"Dr. Roman V. Yampolskiy, Computer Science, Speed School, University of Louisville, KY" 226: 176: 810:. Technically Sentient. 20 September 2015. Archived from the original on 7 August 2016 1276: 1251: 1069: 823: 787: 357: 344: 331: 318: 305: 235: 188: 1298: 1171: 1019: 408: 135: 64: 1236: 1216: 1206: 1196: 1130: 1064: 898: 1059: 931: 1366: 1266: 1211: 1181: 231: 210:
Yampolskiy is an author of some 100 publications, including numerous books.
1256: 1186: 999: 99: 808:"Intellectology and Other Ideas: A Review of Artificial Superintelligence" 565: 1261: 1246: 1054: 1014: 378: 289: 285: 246: 192: 95: 1226: 1201: 1176: 1135: 1115: 919: 499: 184: 26: 892:
http://cecs.louisville.edu/ry/TuringTestasaDefiningFeature04270003.pdf
730:"Why this AI researcher thinks there's a 99.9% chance AI wipes us out" 409:"International Journal of Biometrics (IJBM) – Inderscience Publishers" 1241: 1231: 1009: 196: 1221: 875: 592:"Artificial stupidity could help save humanity from an AI takeover" 569: 627:"Checklist of worst-case scenarios could help prepare for evil AI" 975: 913: 477: 343:. Chapman and Hall/CRC Press (Taylor & Francis Group), 2015, 34: 225:
He has suggested that there is no evidence of a solution to the
1155: 373: 302:
Feature Extraction Approaches for Optical Character Recognition
652:"There is no evidence that AI can be controlled, expert says" 566:"Control dangerous AI before it controls us, one expert says" 456:"Programme Committee | Winter Intelligence Conferences" 786:. Chapman and Hall/CRC Press (Taylor & Francis Group). 315:
Computer Security: from Passwords to Behavioral Biometrics
273: 220:
existential risk from advanced artificial intelligence
1035:
Existential risk from artificial general intelligence
500:"Cyber-Security Lab | University of Louisville" 1106:
Center for Human-Compatible Artificial Intelligence
784:
Artificial Superintelligence: a Futuristic Approach
341:
Artificial Superintelligence: a Futuristic Approach
844:"Roman Yampolskiy on Artificial Superintelligence" 284:Yampolskiy has worked on developing the theory of 864: 777: 775: 1364: 1146:Leverhulme Centre for the Future of Intelligence 828:: CS1 maint: bot: original URL status unknown ( 522:"Roman V. Yampolskiy – Google Scholar Citations" 354:AI: Unexplainable, Unpredictable, Uncontrollable 276:space, i.e. the space of non-boring activities. 1141:Institute for Ethics and Emerging Technologies 772: 252:Yampolskiy has been a research advisor of the 1325:Superintelligence: Paths, Dangers, Strategies 1305:Open letter on artificial intelligence (2015) 961: 431:"Automatic Face Recognition:State of the Art" 704:"Pause Giant AI Experiments: An Open Letter" 218:Yampolskiy has warned of the possibility of 328:Game Strategy: a Novel Behavioral Biometric 968: 954: 781: 240:Pause Giant AI Experiments: An Open Letter 63: 874: 1111:Centre for the Study of Existential Risk 676: 624: 589: 1151:Machine Intelligence Research Institute 384:Machine Intelligence Research Institute 254:Machine Intelligence Research Institute 1365: 846:. Singularity Weblog. 7 September 2015 356:. Chapman & Hall/CRC Press, 2024, 330:. Independent University Press, 2009, 16:Latvian computer scientist (born 1979) 949: 926:Interview of Dr. Yampolskiy on EEweb 175:; born 13 August 1979) is a Latvian 727: 563: 183:, known for his work on behavioral 13: 1293:Statement on AI risk of extinction 938:Interview with Afshin Rattansi on 677:McMillan, Tim (28 February 2024). 590:Baraniuk, Chris (23 August 2018). 304:. Briviba Scientific Press, 2007, 279: 14: 1399: 1030:Ethics of artificial intelligence 907: 317:. New Academic Publishing, 2008, 263: 256:, and an AI safety fellow of the 1349: 1348: 1040:Friendly artificial intelligence 883: 858: 836: 800: 747: 721: 696: 670: 644: 625:Baraniuk, Chris (23 May 2016). 618: 609: 1101:Center for Applied Rationality 583: 557: 535: 514: 492: 470: 448: 423: 401: 169:Roman Vladimirovich Yampolskiy 79:Roman Vladimirovich Yampolskiy 1: 782:Yampolskiy, Roman V. (2015). 394: 268:In 2015, Yampolskiy launched 173:Π ΠΎΠΌΠ°Π½ Π’Π»Π°Π΄ΠΈΠΌΠΈΡ€ΠΎΠ²ΠΈΡ‡ Ямпольский 54: 23:Eastern Slavic naming customs 1388:University at Buffalo alumni 1121:Future of Humanity Institute 564:Hsu, Jeremy (1 March 2012). 213: 7: 1383:Latvian computer scientists 1338:Artificial Intelligence Act 1332:Do You Trust This Computer? 934:(talk on superintelligence) 914:Roman Yampolskiy’s Homepage 367: 205:Speed School of Engineering 154:Speed School of Engineering 10: 1404: 920:Cyber Security Lab at UofL 199:. He holds a PhD from the 21:In this name that follows 20: 1346: 1285: 1164: 1091:Alignment Research Center 1083: 1075:Technological singularity 1025:Effective accelerationism 987: 172: 162: 141: 131: 124: 114: 106: 74: 62: 53: 46: 1126:Future of Life Institute 1045:Instrumental convergence 759:Future of Life Institute 708:Future of Life Institute 458:. Winterintelligence.org 436:. Biometrics.cse.msu.edu 295: 245:In an appearance on the 181:University of Louisville 149:University of Louisville 981:artificial intelligence 292:as a defining example. 1050:Intelligence explosion 389:Singularity University 1005:AI capability control 502:. Cecs.louisville.edu 480:. Cecs.louisville.edu 201:University at Buffalo 119:University at Buffalo 1096:Center for AI Safety 932:Rise of the Machines 1311:Our Final Invention 258:Foresight Institute 897:2013-05-22 at the 755:"Roman Yampolskiy" 658:. 12 February 2024 543:"roman yampolskiy" 411:. Inderscience.com 227:AI control problem 177:computer scientist 69:Yampolskiy in 2023 1360: 1359: 1277:Eliezer Yudkowsky 1252:Stuart J. Russell 1070:Superintelligence 940:Going Underground 288:, suggesting the 166: 165: 126:Scientific career 1395: 1352: 1351: 1299:Human Compatible 1272:Roman Yampolskiy 1020:Consequentialism 977:Existential risk 970: 963: 956: 947: 946: 901: 887: 881: 880: 878: 862: 856: 855: 853: 851: 840: 834: 833: 827: 819: 817: 815: 804: 798: 797: 779: 770: 769: 767: 765: 751: 745: 744: 742: 740: 734:Business Insider 725: 719: 718: 716: 714: 700: 694: 693: 691: 689: 674: 668: 667: 665: 663: 648: 642: 641: 639: 637: 622: 616: 613: 607: 606: 604: 602: 587: 581: 580: 578: 576: 561: 555: 554: 552: 550: 539: 533: 532: 530: 528: 518: 512: 511: 509: 507: 496: 490: 489: 487: 485: 474: 468: 467: 465: 463: 452: 446: 445: 443: 441: 435: 427: 421: 420: 418: 416: 405: 174: 136:Computer science 92: 88: 86: 67: 57: 56:Π ΠΎΠΌΠ°Π½ Ямпольский 48:Roman Yampolskiy 44: 43: 1403: 1402: 1398: 1397: 1396: 1394: 1393: 1392: 1363: 1362: 1361: 1356: 1342: 1281: 1237:Steve Omohundro 1217:Geoffrey Hinton 1207:Stephen Hawking 1192:Paul Christiano 1172:Scott Alexander 1160: 1131:Google DeepMind 1079: 1065:Suffering risks 983: 974: 910: 905: 904: 899:Wayback Machine 888: 884: 863: 859: 849: 847: 842: 841: 837: 821: 820: 813: 811: 806: 805: 801: 794: 780: 773: 763: 761: 753: 752: 748: 738: 736: 726: 722: 712: 710: 702: 701: 697: 687: 685: 675: 671: 661: 659: 656:The Independent 650: 649: 645: 635: 633: 623: 619: 614: 610: 600: 598: 588: 584: 574: 572: 562: 558: 548: 546: 541: 540: 536: 526: 524: 520: 519: 515: 505: 503: 498: 497: 493: 483: 481: 476: 475: 471: 461: 459: 454: 453: 449: 439: 437: 433: 429: 428: 424: 414: 412: 407: 406: 402: 397: 370: 298: 286:AI-Completeness 282: 280:AI-Completeness 266: 216: 158: 115:Alma mater 102: 93: 90: 84: 82: 81: 80: 70: 58: 55: 49: 42: 17: 12: 11: 5: 1401: 1391: 1390: 1385: 1380: 1375: 1358: 1357: 1347: 1344: 1343: 1341: 1340: 1335: 1328: 1321: 1314: 1307: 1302: 1295: 1289: 1287: 1283: 1282: 1280: 1279: 1274: 1269: 1264: 1259: 1254: 1249: 1244: 1239: 1234: 1229: 1224: 1219: 1214: 1209: 1204: 1199: 1194: 1189: 1184: 1179: 1174: 1168: 1166: 1162: 1161: 1159: 1158: 1153: 1148: 1143: 1138: 1133: 1128: 1123: 1118: 1113: 1108: 1103: 1098: 1093: 1087: 1085: 1081: 1080: 1078: 1077: 1072: 1067: 1062: 1060:Machine ethics 1057: 1052: 1047: 1042: 1037: 1032: 1027: 1022: 1017: 1012: 1007: 1002: 997: 991: 989: 985: 984: 973: 972: 965: 958: 950: 944: 943: 935: 929: 923: 917: 909: 908:External links 906: 903: 902: 882: 857: 835: 799: 793:978-1482234435 792: 771: 746: 728:Altchek, Ana. 720: 695: 669: 643: 617: 608: 582: 556: 534: 513: 491: 469: 447: 422: 399: 398: 396: 393: 392: 391: 386: 381: 376: 369: 366: 365: 364: 362:978-1032576268 351: 349:978-1482234435 338: 325: 312: 297: 294: 281: 278: 270:intellectology 265: 264:Intellectology 262: 236:Stuart Russell 215: 212: 164: 163: 160: 159: 157: 156: 151: 145: 143: 139: 138: 133: 129: 128: 122: 121: 116: 112: 111: 108: 104: 103: 94: 89:13 August 1979 78: 76: 72: 71: 68: 60: 59: 51: 50: 47: 15: 9: 6: 4: 3: 2: 1400: 1389: 1386: 1384: 1381: 1379: 1378:Living people 1376: 1374: 1371: 1370: 1368: 1355: 1345: 1339: 1336: 1334: 1333: 1329: 1327: 1326: 1322: 1320: 1319: 1318:The Precipice 1315: 1313: 1312: 1308: 1306: 1303: 1301: 1300: 1296: 1294: 1291: 1290: 1288: 1284: 1278: 1275: 1273: 1270: 1268: 1267:Frank Wilczek 1265: 1263: 1260: 1258: 1255: 1253: 1250: 1248: 1245: 1243: 1240: 1238: 1235: 1233: 1230: 1228: 1225: 1223: 1220: 1218: 1215: 1213: 1212:Dan Hendrycks 1210: 1208: 1205: 1203: 1200: 1198: 1195: 1193: 1190: 1188: 1185: 1183: 1182:Yoshua Bengio 1180: 1178: 1175: 1173: 1170: 1169: 1167: 1163: 1157: 1154: 1152: 1149: 1147: 1144: 1142: 1139: 1137: 1134: 1132: 1129: 1127: 1124: 1122: 1119: 1117: 1114: 1112: 1109: 1107: 1104: 1102: 1099: 1097: 1094: 1092: 1089: 1088: 1086: 1084:Organizations 1082: 1076: 1073: 1071: 1068: 1066: 1063: 1061: 1058: 1056: 1053: 1051: 1048: 1046: 1043: 1041: 1038: 1036: 1033: 1031: 1028: 1026: 1023: 1021: 1018: 1016: 1013: 1011: 1008: 1006: 1003: 1001: 998: 996: 993: 992: 990: 986: 982: 978: 971: 966: 964: 959: 957: 952: 951: 948: 942: 941: 936: 933: 930: 927: 924: 921: 918: 915: 912: 911: 900: 896: 893: 886: 877: 872: 868: 861: 845: 839: 831: 825: 809: 803: 795: 789: 785: 778: 776: 760: 756: 750: 735: 731: 724: 709: 705: 699: 684: 680: 673: 657: 653: 647: 632: 631:New Scientist 628: 621: 612: 597: 596:New Scientist 593: 586: 571: 567: 560: 544: 538: 523: 517: 501: 495: 479: 473: 457: 451: 432: 426: 410: 404: 400: 390: 387: 385: 382: 380: 377: 375: 372: 371: 363: 359: 355: 352: 350: 346: 342: 339: 337: 336:0-578-03685-1 333: 329: 326: 324: 323:0-6152-1818-0 320: 316: 313: 311: 310:0-6151-5511-1 307: 303: 300: 299: 293: 291: 287: 277: 275: 271: 261: 259: 255: 250: 248: 243: 241: 237: 233: 232:Yoshua Bengio 228: 223: 221: 211: 208: 206: 202: 198: 194: 190: 186: 182: 178: 170: 161: 155: 152: 150: 147: 146: 144: 140: 137: 134: 130: 127: 123: 120: 117: 113: 109: 105: 101: 97: 91:(age 45) 77: 73: 66: 61: 52: 45: 40: 36: 33: and the 32: 31:Vladimirovich 28: 24: 19: 1330: 1323: 1316: 1309: 1297: 1271: 1257:Jaan Tallinn 1197:Eric Drexler 1187:Nick Bostrom 1000:AI alignment 939: 885: 866: 860: 848:. Retrieved 838: 812:. Retrieved 802: 783: 762:. Retrieved 758: 749: 737:. Retrieved 733: 723: 711:. Retrieved 707: 698: 686:. Retrieved 682: 672: 660:. Retrieved 655: 646: 634:. Retrieved 630: 620: 611: 599:. Retrieved 595: 585: 573:. Retrieved 559: 549:25 September 547:. Retrieved 545:. Amazon.com 537: 527:25 September 525:. Retrieved 516: 506:25 September 504:. Retrieved 494: 484:25 September 482:. Retrieved 472: 462:25 September 460:. Retrieved 450: 440:25 September 438:. Retrieved 425: 415:25 September 413:. Retrieved 403: 353: 340: 327: 314: 301: 283: 269: 267: 251: 244: 238:in signing " 224: 217: 209: 168: 167: 142:Institutions 125: 100:Soviet Union 38: 30: 18: 1373:1979 births 1262:Max Tegmark 1247:Martin Rees 1055:Longtermism 1015:AI takeover 850:22 November 814:22 November 683:The Debrief 379:AI-complete 290:Turing Test 247:Lex Fridman 193:cyberworlds 107:Nationality 96:Latvian SSR 35:family name 1367:Categories 1227:Shane Legg 1202:Sam Harris 1177:Sam Altman 1116:EleutherAI 876:1606.07092 575:28 January 395:References 185:biometrics 171:(Russian: 85:1979-08-13 39:Yampolskiy 27:patronymic 1242:Huw Price 1232:Elon Musk 1136:Humanity+ 1010:AI safety 214:AI safety 197:AI safety 1354:Category 1222:Bill Joy 988:Concepts 895:Archived 824:cite web 636:12 April 601:12 April 570:NBC News 368:See also 189:security 739:13 June 179:at the 110:Latvian 1165:People 1156:OpenAI 790:  764:3 July 713:4 July 688:4 July 662:4 July 374:AI box 360:  347:  334:  321:  308:  195:, and 132:Fields 25:, the 1286:Other 979:from 871:arXiv 434:(PDF) 296:Books 852:2016 830:link 816:2016 788:ISBN 766:2024 741:2024 715:2024 690:2024 664:2024 638:2020 603:2020 577:2016 551:2012 529:2012 508:2012 486:2012 464:2012 442:2012 417:2012 358:ISBN 345:ISBN 332:ISBN 319:ISBN 306:ISBN 242:". 234:and 75:Born 995:AGI 274:fun 191:of 37:is 29:is 1369:: 869:. 826:}} 822:{{ 774:^ 757:. 732:. 706:. 681:. 654:. 629:. 594:. 568:. 260:. 207:. 187:, 98:, 87:) 969:e 962:t 955:v 928:. 922:. 916:. 879:. 873:: 854:. 832:) 818:. 796:. 768:. 743:. 717:. 692:. 666:. 640:. 605:. 579:. 553:. 531:. 510:. 488:. 466:. 444:. 419:. 83:( 41:.

Index

Eastern Slavic naming customs
patronymic
family name

Latvian SSR
Soviet Union
University at Buffalo
Computer science
University of Louisville
Speed School of Engineering
computer scientist
University of Louisville
biometrics
security
cyberworlds
AI safety
University at Buffalo
Speed School of Engineering
existential risk from advanced artificial intelligence
AI control problem
Yoshua Bengio
Stuart Russell
Pause Giant AI Experiments: An Open Letter
Lex Fridman
Machine Intelligence Research Institute
Foresight Institute
fun
AI-Completeness
Turing Test
ISBN

Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.

↑