Birdwatch Archive

Birdwatch Note Rating

2024-04-08 22:16:05 UTC - HELPFUL

Rated by Participant: 4729A55B0D099D2ED5638F8B9595FBAF7AA8E3037233082E08AA2BA0CEF98542
Participant Details

Original Note:

O estudo avaliou a resistência de modelos de IA contra ataques de jailbreak. No estudo, modelos como o ChatGPT, Grok, Gemini e Claude falharam em algum teste, com exceção do modelo Llama. Os modelos Grok e Le chat tiveram os piores resultados, seguidos pelo ChatGPT e Gemini. https://adversa.ai/blog/llm-red-teaming-vs-grok-chatgpt-claude-gemini-bing-mistral-llama

All Note Details

Original Tweet

All Information

  • noteId - 1777433738424500647
  • participantId -
  • raterParticipantId - 4729A55B0D099D2ED5638F8B9595FBAF7AA8E3037233082E08AA2BA0CEF98542
  • createdAtMillis - 1712614565003
  • version - 2
  • agree - 0
  • disagree - 0
  • helpful - 0
  • notHelpful - 0
  • helpfulnessLevel - HELPFUL
  • helpfulOther - 0
  • helpfulInformative - 0
  • helpfulClear - 0
  • helpfulEmpathetic - 0
  • helpfulGoodSources - 1
  • helpfulUniqueContext - 0
  • helpfulAddressesClaim - 1
  • helpfulImportantContext - 0
  • helpfulUnbiasedLanguage - 1
  • notHelpfulOther - 0
  • notHelpfulIncorrect - 0
  • notHelpfulSourcesMissingOrUnreliable - 0
  • notHelpfulOpinionSpeculationOrBias - 0
  • notHelpfulMissingKeyPoints - 0
  • notHelpfulOutdated - 0
  • notHelpfulHardToUnderstand - 0
  • notHelpfulArgumentativeOrBiased - 0
  • notHelpfulOffTopic - 0
  • notHelpfulSpamHarassmentOrAbuse - 0
  • notHelpfulIrrelevantSources - 0
  • notHelpfulOpinionSpeculation - 0
  • notHelpfulNoteNotNeeded - 0
  • ratingsId - 17774337384245006474729A55B0D099D2ED5638F8B9595FBAF7AA8E3037233082E08AA2BA0CEF98542