Birdwatch Archive

Birdwatch Note Rating

2023-07-21 18:44:56 UTC - SOMEWHAT_HELPFUL

Rated by Participant: 3CBA5AD3AF48DC23B1A1F310918CA121FCE2D6E5F46E59568D34DD169106E546
Participant Details

Original Note:

GPT-4 was never really able to do the task they were testing - checking whether a number is prime. It just reversed from usually saying numbers were prime to usually saying they were non-prime. When tested on just prime numbers this made it look like it was getting worse. https://www.aisnakeoil.com/p/is-gpt-4-getting-worse-over-time

All Note Details

Original Tweet

All Information

  • noteId - 1682415491724222466
  • participantId -
  • raterParticipantId - 3CBA5AD3AF48DC23B1A1F310918CA121FCE2D6E5F46E59568D34DD169106E546
  • createdAtMillis - 1689965096602
  • version - 2
  • agree - 0
  • disagree - 0
  • helpful - 0
  • notHelpful - 0
  • helpfulnessLevel - SOMEWHAT_HELPFUL
  • helpfulOther - 0
  • helpfulInformative - 0
  • helpfulClear - 0
  • helpfulEmpathetic - 0
  • helpfulGoodSources - 0
  • helpfulUniqueContext - 0
  • helpfulAddressesClaim - 1
  • helpfulImportantContext - 0
  • helpfulUnbiasedLanguage - 0
  • notHelpfulOther - 0
  • notHelpfulIncorrect - 0
  • notHelpfulSourcesMissingOrUnreliable - 0
  • notHelpfulOpinionSpeculationOrBias - 0
  • notHelpfulMissingKeyPoints - 0
  • notHelpfulOutdated - 0
  • notHelpfulHardToUnderstand - 0
  • notHelpfulArgumentativeOrBiased - 1
  • notHelpfulOffTopic - 0
  • notHelpfulSpamHarassmentOrAbuse - 0
  • notHelpfulIrrelevantSources - 0
  • notHelpfulOpinionSpeculation - 1
  • notHelpfulNoteNotNeeded - 0
  • ratingsId - 16824154917242224663CBA5AD3AF48DC23B1A1F310918CA121FCE2D6E5F46E59568D34DD169106E546