Knowledge

Eugene Goostman

Source đź“ť

239:", Turing predicted that by the year 2000, computer programs would be sufficiently advanced that the average interrogator would, after five minutes of questioning, "not have more than 70 per cent chance" of correctly guessing whether they were speaking to a human or a machine. Although Turing phrased this as a prediction rather than a "threshold for intelligence", commentators believe that Warwick had chosen to interpret it as meaning that if 30% of interrogators were fooled, the software had "passed the Turing test". 81:. Veselov stated that Goostman was designed to be a "character with a believable personality". The choice of age was intentional, as, in Veselov's opinion, a thirteen-year-old is "not too old to know everything and not too young to know nothing". Goostman's young age also induces people who "converse" with him to forgive minor grammatical errors in his responses. In 2014, work was made on improving the bot's "dialog controller", allowing Goostman to output more human-like dialogue. 57:, that by the year 2000, machines would be capable of fooling 30% of human judges after five minutes of questioning. The validity and relevance of the announcement of Goostman's pass was questioned by critics, who noted the exaggeration of the achievement by Warwick, the bot's use of personality quirks and humour in an attempt to misdirect users from its non-human tendencies and lack of real intelligence, along with "passes" achieved by other chatbots at similar events. 248: 34:
in 2001 by a group of three programmers, the Russian-born Vladimir Veselov, Ukrainian-born Eugene Demchenko, and Russian-born Sergey Ulasen, Goostman is portrayed as a 13-year-old Ukrainian boy—characteristics that are intended to induce forgiveness in those with whom it interacts for its grammatical
230:
Some will claim that the Test has already been passed. The words Turing Test have been applied to similar competitions around the world. However this event involved more simultaneous comparison tests than ever before, was independently verified and, crucially, the conversations were unrestricted. A
277:
was critical of Warwick's claims, arguing that Goostman's "success" was only the result of a "cleverly-coded piece of software", going on to say that "it's easy to see how an untrained judge might mistake wit for reality, but once you have an understanding of how this sort of system works, the
312:
on its content. Marcus stated that "no existing combination of hardware and software can learn completely new things at will the way a clever child can." However, he still believed that there were potential uses for technology such as that of Goostman, specifically suggesting the creation of
173:. The competition, which featured five bots, twenty-five hidden humans, and thirty judges, was considered to be the largest-ever Turing test contest by its organizers. After a series of five-minute-long text conversations, 29% of the judges were convinced that the bot was an actual human. 258:
Warwick's claim that Eugene Goostman was the first ever chatbot to pass a Turing test was met with scepticism; critics acknowledged similar "passes" made in the past by other chatbots under the 30% criteria, including PC Therapist in 1991 (which tricked 5 of 10 judges, 50%), and at the
307:
respectively—as examples of computer systems that show a degree of intelligence in their specialised field, he further argued that they were not an equivalent to a computer system that shows "broad" intelligence, and could—for example, watch a television programme and
222:. Each judge partook in a textual conversation with each of the five bots; at the same time, they also conversed with a human. In all, a total of 300 conversations were conducted. In Warwick's view, this made Goostman the first machine to pass a Turing test. In a 474: 765: 818: 537: 679: 795: 193:
to mark the 60th anniversary of Turing's death, Goostman won after 33% of the judges were convinced that the bot was human. 30 judges took part in the event, which included
466: 757: 378: 826: 529: 49:
On 7 June 2014, at a contest marking the 60th anniversary of Turing's death, 33% of the event's judges thought that Goostman was human; the event's organiser
504: 46:, Goostman won a competition promoted as the largest-ever Turing test contest, in which it successfully convinced 29% of its judges that it was human. 319:
professor Murray Shanahan questioned the validity and scientific basis of the test, stating that it was "completely misplaced, and it devalues real
671: 735: 411: 649: 597: 787: 870: 623: 154: 111:
Something between 2 and 4. Maybe, three? :-))) By the way, I still don’t know your specialty – or, possibly, I’ve missed it?
254:
considered Goostman to be the first machine to "pass" a Turing test, although the validity of his claim was disputed by critics.
126:
No, I need to know that you're not a chatbot. Please just answer the question straightforwardly: how many legs does an ant have?
38:
The Goostman bot has competed in a number of Turing test contests since its creation, and finished second in the 2005 and 2008
236: 54: 271:, argued that Turing tests can only prove that a machine can "imitate" intelligence rather than show actual intelligence. 374: 323:
research. It makes it seem like science fiction AI is nearly here, when in fact it's not and it's incredibly difficult."
335:, was also skeptical, questioning publicity blunders such as the five chatbots being referred to in press releases as " 436: 564:"My Conversation with "Eugene Goostman," the Chatbot that's All Over the News for Allegedly Passing the Turing Test" 496: 571: 282:
and deflection becomes obvious, even irritating. The illusion, in other words, is fleeting." While acknowledging
267:
tricked 59.3% of 1334 votes (which included the 30 judges, along with an audience). Cleverbot's developer,
352: 206: 194: 101:
I can’t make a choice right now. I should think it out later. And I forgot to ask you where you are from…
42:
contest. In June 2012, at an event marking what would have been the 100th birthday of the test's author,
727: 467:"No, A 'Supercomputer' Did NOT Pass The Turing Test for the First Time And Everyone Should Know Better" 287: 645: 593: 339:", and saying that "creating a chatbot that can fool humans is not really the same thing as creating 672:"Computer allegedly passes Turing Test for first time by convincing judges it is a 13-year-old boy" 407: 53:
considered it to have passed Turing's test as a result, per Turing's prediction in his 1950 paper
340: 320: 316: 198: 190: 131:
Something between 2 and 4. Maybe three? :-))) Oh, what a fruitful conversation ;-)
30:, a test of a computer's ability to communicate indistinguishably from a human. Developed in 279: 619: 121:
Just two, but Chernobyl mutants may have up two five. I know you are supposed to trick me.
8: 702: 309: 865: 291: 219: 166: 31: 149:
contest; it finished joint second in the Loebner test in 2001, and came second to
268: 231:
true Turing Test does not set the questions or topics prior to the conversations.
559: 158: 85: 850: 859: 336: 251: 223: 186: 182: 162: 146: 78: 50: 39: 728:"Someone on the internet ISN'T a 13-year-old boy: Bot beats off Turing Test" 563: 326: 202: 274: 170: 150: 142: 43: 27: 819:"'Captain Cyborg': the man behind the controversial Turing Test claims" 209: 74: 303: 299: 264: 260: 214: 157:
in 2008. On 23 June 2012, Goostman won a Turing test competition at
331: 70: 23: 497:"World to Captain Cyborg on 'Turing test' stunt: You're Rumbled" 247: 295: 66: 65:
Eugene Goostman is portrayed as being a 13-year-old boy from
594:"2001 Loebner Prize Competition in Artificial Intelligence" 375:"Computer chatbot 'Eugene Goostman' passes the Turing test" 294:
projects—single-purpose computer systems meant for playing
408:"Turing Test success marks milestone in computing history" 283: 810: 530:"Bot with boyish personality wins biggest Turing test" 788:"No Skynet: Turing test 'success' isn't all it seems" 703:"That Computer Actually Got an F on the Turing Test" 181:
On 7 June 2014, in a Turing test competition at the
460: 458: 758:"Software tricks people into thinking it is human" 552: 369: 367: 313:"believable", interactive video game characters. 857: 750: 664: 455: 431: 429: 780: 720: 524: 522: 364: 263:festival in 2011, where a modified version of 426: 402: 400: 398: 396: 694: 568:Shtetl-Optimized, The Blog of Scott Aaronson 519: 141:Eugene Goostman has competed in a number of 96:Which is bigger, a shoebox or Mount Everest? 16:Chatbot that arguably passed the Turing test 197:, a sponsor of Turing's posthumous pardon, 393: 700: 558: 246: 176: 464: 858: 410:. University of Reading. 8 June 2014. 35:errors and lack of general knowledge. 26:that some regard as having passed the 816: 489: 237:Computing Machinery and Intelligence 116:How many legs does a millipede have? 88:and Eugene Goostman ran as follows: 55:Computing Machinery and Intelligence 652:from the original on 9 January 2015 600:from the original on 9 January 2015 437:"What comes after the Turing Test?" 13: 574:from the original on 7 August 2014 14: 882: 844: 798:from the original on 10 June 2014 768:from the original on 11 June 2015 738:from the original on 11 June 2014 507:from the original on 14 June 2014 477:from the original on 10 June 2014 381:from the original on 12 June 2014 682:from the original on 9 June 2014 648:. Loebner.net. 12 October 2008. 626:from the original on 4 July 2013 596:. Loebner.net. 25 October 2001. 540:from the original on 4 July 2014 414:from the original on 8 June 2014 106:How many legs does a camel have? 638: 136: 612: 586: 60: 1: 817:Edgar, James (10 June 2014). 465:Masnick, Mike (9 June 2014). 358: 242: 145:competitions, including the 7: 353:Natural language processing 346: 207:Fellow of the Royal Society 10: 887: 871:Human–computer interaction 701:Adam Mann (9 June 2014). 620:"2005 Summary of Results" 851:Eugene Goostman webpage 341:artificial intelligence 317:Imperial College London 199:artificial intelligence 84:A conversation between 377:. ZDNet. 8 June 2014. 255: 233: 134: 77:and a father who is a 329:, editor of the blog 250: 228: 191:University of Reading 90: 764:. 6 September 2011. 646:"Loebner Prize 2008" 235:In his 1950 paper " 165:, held to mark the 256: 792:The New Scientist 762:The New Scientist 226:, he added that: 169:of its namesake, 878: 839: 838: 836: 834: 825:. Archived from 814: 808: 807: 805: 803: 784: 778: 777: 775: 773: 754: 748: 747: 745: 743: 724: 718: 717: 715: 713: 698: 692: 691: 689: 687: 668: 662: 661: 659: 657: 642: 636: 635: 633: 631: 616: 610: 609: 607: 605: 590: 584: 583: 581: 579: 562:(19 June 2014). 556: 550: 549: 547: 545: 536:. 25 June 2012. 526: 517: 516: 514: 512: 503:. 10 June 2014. 493: 487: 486: 484: 482: 462: 453: 452: 450: 448: 433: 424: 423: 421: 419: 404: 391: 390: 388: 386: 371: 310:answer questions 220:Robert Llewellyn 73:, who has a pet 32:Saint Petersburg 886: 885: 881: 880: 879: 877: 876: 875: 856: 855: 847: 842: 832: 830: 829:on 10 June 2014 815: 811: 801: 799: 794:. 9 June 2014. 786: 785: 781: 771: 769: 756: 755: 751: 741: 739: 726: 725: 721: 711: 709: 699: 695: 685: 683: 678:. 8 June 2014. 670: 669: 665: 655: 653: 644: 643: 639: 629: 627: 622:. Loebner.net. 618: 617: 613: 603: 601: 592: 591: 587: 577: 575: 560:Aaronson, Scott 557: 553: 543: 541: 528: 527: 520: 510: 508: 495: 494: 490: 480: 478: 463: 456: 446: 444: 435: 434: 427: 417: 415: 406: 405: 394: 384: 382: 373: 372: 365: 361: 349: 269:Rollo Carpenter 245: 185:, organised by 179: 153:in 2005 and to 139: 133: 127: 122: 117: 112: 107: 102: 97: 63: 20:Eugene Goostman 17: 12: 11: 5: 884: 874: 873: 868: 854: 853: 846: 845:External links 843: 841: 840: 809: 779: 749: 719: 693: 663: 637: 611: 585: 551: 518: 488: 454: 441:The New Yorker 425: 392: 362: 360: 357: 356: 355: 348: 345: 337:supercomputers 244: 241: 178: 175: 159:Bletchley Park 138: 135: 91: 86:Scott Aaronson 62: 59: 15: 9: 6: 4: 3: 2: 883: 872: 869: 867: 864: 863: 861: 852: 849: 848: 828: 824: 823:The Telegraph 820: 813: 797: 793: 789: 783: 767: 763: 759: 753: 737: 733: 729: 723: 708: 704: 697: 681: 677: 673: 667: 651: 647: 641: 625: 621: 615: 599: 595: 589: 573: 569: 565: 561: 555: 539: 535: 534:New Scientist 531: 525: 523: 506: 502: 498: 492: 476: 472: 468: 461: 459: 443:. 9 June 2014 442: 438: 432: 430: 413: 409: 403: 401: 399: 397: 380: 376: 370: 368: 363: 354: 351: 350: 344: 342: 338: 334: 333: 328: 324: 322: 318: 314: 311: 306: 305: 301: 297: 293: 289: 285: 281: 276: 272: 270: 266: 262: 253: 252:Kevin Warwick 249: 240: 238: 232: 227: 225: 224:press release 221: 217: 216: 211: 208: 204: 200: 196: 192: 188: 187:Kevin Warwick 184: 183:Royal Society 174: 172: 168: 164: 163:Milton Keynes 160: 156: 152: 148: 147:Loebner Prize 144: 132: 130: 125: 120: 115: 110: 105: 100: 95: 89: 87: 82: 80: 79:gynaecologist 76: 72: 68: 58: 56: 52: 51:Kevin Warwick 47: 45: 41: 40:Loebner Prize 36: 33: 29: 25: 21: 831:. Retrieved 827:the original 822: 812: 800:. Retrieved 791: 782: 770:. Retrieved 761: 752: 740:. Retrieved 732:The Register 731: 722: 710:. Retrieved 706: 696: 684:. Retrieved 675: 666: 654:. Retrieved 640: 628:. Retrieved 614: 602:. Retrieved 588: 578:12 September 576:. Retrieved 567: 554: 542:. Retrieved 533: 509:. Retrieved 501:The Register 500: 491: 479:. Retrieved 470: 445:. Retrieved 440: 416:. Retrieved 383:. Retrieved 330: 327:Mike Masnick 325: 315: 302: 280:misdirection 273: 257: 234: 229: 213: 203:Aaron Sloman 195:Lord Sharkey 180: 140: 137:Competitions 128: 123: 118: 113: 108: 103: 98: 93: 92: 83: 64: 48: 37: 19: 18: 275:Gary Marcus 177:2014 "pass" 171:Alan Turing 151:Jabberwacky 143:Turing test 61:Personality 44:Alan Turing 28:Turing test 860:Categories 359:References 210:Mark Pagel 201:Professor 75:guinea pig 676:The Verge 304:Jeopardy! 300:quiz show 288:Deep Blue 278:constant 265:Cleverbot 261:Techniche 243:Reactions 215:Red Dwarf 167:centenary 866:Chatbots 796:Archived 766:Archived 736:Archived 680:Archived 650:Archived 624:Archived 598:Archived 572:Archived 538:Archived 505:Archived 475:Archived 471:Techdirt 412:Archived 379:Archived 347:See also 332:Techdirt 298:and the 833:11 June 656:13 June 630:13 June 604:13 June 511:10 June 189:of the 129:Eugene: 119:Eugene: 109:Eugene: 99:Eugene: 71:Ukraine 24:chatbot 802:9 June 772:9 June 742:9 June 712:9 June 686:8 June 544:8 June 481:9 June 447:9 June 418:8 June 385:8 June 292:Watson 218:actor 124:Scott: 114:Scott: 104:Scott: 94:Scott: 707:Wired 296:chess 155:Elbot 67:Odesa 22:is a 835:2014 804:2014 774:2014 744:2014 714:2014 688:2014 658:2014 632:2014 606:2014 580:2014 546:2014 513:2014 483:2014 449:2014 420:2014 387:2014 290:and 212:and 343:." 286:'s 284:IBM 161:in 862:: 821:. 790:. 760:. 734:. 730:. 705:. 674:. 570:. 566:. 532:. 521:^ 499:. 473:. 469:. 457:^ 439:. 428:^ 395:^ 366:^ 321:AI 205:, 69:, 837:. 806:. 776:. 746:. 716:. 690:. 660:. 634:. 608:. 582:. 548:. 515:. 485:. 451:. 422:. 389:.

Index

chatbot
Turing test
Saint Petersburg
Loebner Prize
Alan Turing
Kevin Warwick
Computing Machinery and Intelligence
Odesa
Ukraine
guinea pig
gynaecologist
Scott Aaronson
Turing test
Loebner Prize
Jabberwacky
Elbot
Bletchley Park
Milton Keynes
centenary
Alan Turing
Royal Society
Kevin Warwick
University of Reading
Lord Sharkey
artificial intelligence
Aaron Sloman
Fellow of the Royal Society
Mark Pagel
Red Dwarf
Robert Llewellyn

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

↑