Birdwatch Archive

Birdwatch Note Rating

2023-11-30 15:39:45 UTC - NOT_HELPFUL

Rated by Participant: 237BC62BBA001B75EEEEFC1D43AE64A037C41E78AB9101E231F094561923BDC3
Participant Details

Original Note:

https://t.co/97exJtFHWC The paper details an adversarial attack method on GPT. No way to know output context as prompts or photoshop could create this. In any case, as of the time of this writing this adversarial attack apparently no longer works.

All Note Details

Original Tweet

All Information

  • noteId - 1730225511547240826
  • participantId -
  • raterParticipantId - 237BC62BBA001B75EEEEFC1D43AE64A037C41E78AB9101E231F094561923BDC3
  • createdAtMillis - 1701358785049
  • version - 2
  • agree - 0
  • disagree - 0
  • helpful - 0
  • notHelpful - 0
  • helpfulnessLevel - NOT_HELPFUL
  • helpfulOther - 0
  • helpfulInformative - 0
  • helpfulClear - 0
  • helpfulEmpathetic - 0
  • helpfulGoodSources - 0
  • helpfulUniqueContext - 0
  • helpfulAddressesClaim - 0
  • helpfulImportantContext - 0
  • helpfulUnbiasedLanguage - 0
  • notHelpfulOther - 0
  • notHelpfulIncorrect - 0
  • notHelpfulSourcesMissingOrUnreliable - 1
  • notHelpfulOpinionSpeculationOrBias - 0
  • notHelpfulMissingKeyPoints - 0
  • notHelpfulOutdated - 0
  • notHelpfulHardToUnderstand - 1
  • notHelpfulArgumentativeOrBiased - 0
  • notHelpfulOffTopic - 0
  • notHelpfulSpamHarassmentOrAbuse - 0
  • notHelpfulIrrelevantSources - 0
  • notHelpfulOpinionSpeculation - 1
  • notHelpfulNoteNotNeeded - 0
  • ratingsId - 1730225511547240826237BC62BBA001B75EEEEFC1D43AE64A037C41E78AB9101E231F094561923BDC3