Birdwatch Archive

Birdwatch Note Rating

2025-01-29 06:32:24 UTC - HELPFUL

Rated by Participant: 0DB8E7EB8B757E88CA6DADB79577F8E079633F19059036037C321A715FCCA02B
Participant Details

Original Note:

You don't make a reasoning model from distillation. OpenAI doesn't expose their reasoning. DeepSeek used distillation - but not at all how Sacks describes it here. DeepSeek released a "distilled" Llama model. It was distilled from R1. NOT OpenAI. https://deepinfra.com/deepseek-ai/DeepSeek-R1-Distill-Llama-70B

All Note Details

Original Tweet

All Information

  • noteId - 1884442204099469439
  • participantId -
  • raterParticipantId - 0DB8E7EB8B757E88CA6DADB79577F8E079633F19059036037C321A715FCCA02B
  • createdAtMillis - 1738132344764
  • version - 2
  • agree - 0
  • disagree - 0
  • helpful - 0
  • notHelpful - 0
  • helpfulnessLevel - HELPFUL
  • helpfulOther - 0
  • helpfulInformative - 0
  • helpfulClear - 1
  • helpfulEmpathetic - 0
  • helpfulGoodSources - 1
  • helpfulUniqueContext - 0
  • helpfulAddressesClaim - 1
  • helpfulImportantContext - 1
  • 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 - 18844422040994694390DB8E7EB8B757E88CA6DADB79577F8E079633F19059036037C321A715FCCA02B