Birdwatch Archive

Birdwatch Note

2023-07-21 15:41:25 UTC - MISINFORMED_OR_POTENTIALLY_MISLEADING

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

Written by ADB91A3245808E77E001C0573A3EDFB5CF54E507DE1B8AF91EBB0E562E144A46
Participant Details

Original Tweet

Tweet embedding is no longer reliably available, due to the platform's instability (in terms of both technology and policy). If the Tweet still exists, you can view it here: https://twitter.com/foo_bar/status/1682399725243322369

Please note, though, that you may need to have your own Twitter account to access that page. I am currently exploring options for archiving Tweet data in a post-API context.

All Information

  • ID - 1682415491724222466
  • noteId - 1682415491724222466
  • participantId -
  • noteAuthorParticipantId - ADB91A3245808E77E001C0573A3EDFB5CF54E507DE1B8AF91EBB0E562E144A46 Participant Details
  • createdAtMillis - 1689954085653
  • tweetId - 1682399725243322369
  • classification - MISINFORMED_OR_POTENTIALLY_MISLEADING
  • believable -
  • harmful -
  • validationDifficulty -
  • misleadingOther - 0
  • misleadingFactualError - 1
  • misleadingManipulatedMedia - 0
  • misleadingOutdatedInformation - 0
  • misleadingMissingImportantContext - 1
  • misleadingUnverifiedClaimAsFact - 0
  • misleadingSatire - 0
  • notMisleadingOther - 0
  • notMisleadingFactuallyCorrect - 0
  • notMisleadingOutdatedButNotWhenWritten - 0
  • notMisleadingClearlySatire - 0
  • notMisleadingPersonalOpinion - 0
  • trustworthySources - 1
  • summary
    • 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

Note Status History

createdAt timestampMillisOfFirstNonNMRStatus firstNonNMRStatus timestampMillisOfCurrentStatus currentStatus timestampMillisOfLatestNonNMRStatus mostRecentNonNMRStatus participantId
2023-07-21 15:41:25 UTC
(1689954085653)
1969-12-31 23:59:59 UTC
(-1)
2023-07-22 02:12:19 UTC
(1689991939774)
NEEDS_MORE_RATINGS 1969-12-31 23:59:59 UTC
(-1)

Note Ratings

rated at rated by
2023-07-21 19:29:16 -0500 Rating Details
2023-07-21 19:15:55 -0500 Rating Details
2023-07-21 19:12:52 -0500 Rating Details
2023-07-21 19:09:31 -0500 Rating Details
2023-07-21 19:07:33 -0500 Rating Details
2023-07-21 19:02:07 -0500 Rating Details
2023-07-21 18:55:26 -0500 Rating Details
2023-07-21 18:46:22 -0500 Rating Details
2023-07-21 18:32:12 -0500 Rating Details
2023-07-21 18:23:00 -0500 Rating Details
2023-07-21 18:19:28 -0500 Rating Details
2023-07-21 18:13:50 -0500 Rating Details
2023-07-21 18:05:35 -0500 Rating Details
2023-07-21 18:03:31 -0500 Rating Details
2023-07-21 17:59:10 -0500 Rating Details
2023-07-21 17:58:11 -0500 Rating Details
2023-07-21 17:57:12 -0500 Rating Details
2023-07-21 17:57:09 -0500 Rating Details
2023-07-21 17:56:58 -0500 Rating Details
2023-07-21 17:55:29 -0500 Rating Details
2023-07-21 17:47:02 -0500 Rating Details
2023-07-21 17:44:22 -0500 Rating Details
2023-07-21 17:40:04 -0500 Rating Details
2023-07-21 17:38:55 -0500 Rating Details
2023-07-21 17:38:15 -0500 Rating Details
2023-07-21 17:37:59 -0500 Rating Details
2023-07-21 17:35:50 -0500 Rating Details
2023-07-21 17:35:37 -0500 Rating Details
2023-07-21 17:28:26 -0500 Rating Details
2023-07-21 17:27:57 -0500 Rating Details
2023-07-21 17:25:28 -0500 Rating Details
2023-07-21 17:24:11 -0500 Rating Details
2023-07-21 17:20:42 -0500 Rating Details
2023-07-21 17:15:14 -0500 Rating Details
2023-07-21 17:13:29 -0500 Rating Details
2023-07-21 17:13:28 -0500 Rating Details
2023-07-21 17:13:11 -0500 Rating Details
2023-07-21 17:12:45 -0500 Rating Details
2023-07-21 17:12:34 -0500 Rating Details
2023-07-21 17:06:45 -0500 Rating Details
2023-07-21 17:05:46 -0500 Rating Details
2023-07-21 17:02:26 -0500 Rating Details
2023-07-21 17:01:19 -0500 Rating Details
2023-07-21 16:59:22 -0500 Rating Details
2023-07-21 16:54:24 -0500 Rating Details
2023-07-21 16:53:56 -0500 Rating Details
2023-07-21 16:52:45 -0500 Rating Details
2023-07-21 16:51:12 -0500 Rating Details
2023-07-21 16:48:59 -0500 Rating Details
2023-07-21 16:47:04 -0500 Rating Details
2023-07-21 16:46:01 -0500 Rating Details
2023-07-21 16:44:39 -0500 Rating Details
2023-07-21 16:43:41 -0500 Rating Details
2023-07-21 16:42:41 -0500 Rating Details
2023-07-21 16:40:38 -0500 Rating Details
2023-07-21 16:37:57 -0500 Rating Details
2023-07-21 16:28:58 -0500 Rating Details
2023-07-21 16:28:17 -0500 Rating Details
2023-07-21 16:25:35 -0500 Rating Details
2023-07-21 16:22:45 -0500 Rating Details
2023-07-21 16:18:35 -0500 Rating Details
2023-07-21 16:17:28 -0500 Rating Details
2023-07-21 16:15:46 -0500 Rating Details
2023-07-21 16:14:17 -0500 Rating Details
2023-07-21 16:09:53 -0500 Rating Details
2023-07-21 16:03:14 -0500 Rating Details
2023-07-21 16:02:39 -0500 Rating Details
2023-07-21 16:00:17 -0500 Rating Details
2023-07-21 15:58:55 -0500 Rating Details
2023-07-21 15:52:57 -0500 Rating Details
2023-07-21 15:47:19 -0500 Rating Details
2023-07-21 15:46:18 -0500 Rating Details
2023-07-21 15:45:57 -0500 Rating Details
2023-07-21 15:44:11 -0500 Rating Details
2023-07-21 15:39:01 -0500 Rating Details
2023-07-21 15:36:35 -0500 Rating Details
2023-07-21 15:36:10 -0500 Rating Details
2023-07-21 15:33:51 -0500 Rating Details
2023-07-21 15:33:11 -0500 Rating Details
2023-07-21 15:32:55 -0500 Rating Details
2023-07-21 15:28:04 -0500 Rating Details
2023-07-21 15:25:17 -0500 Rating Details
2023-07-21 15:21:55 -0500 Rating Details
2023-07-21 15:20:32 -0500 Rating Details
2023-07-21 15:03:06 -0500 Rating Details
2023-07-21 15:02:27 -0500 Rating Details
2023-07-21 15:00:37 -0500 Rating Details
2023-07-21 14:58:37 -0500 Rating Details
2023-07-21 14:57:23 -0500 Rating Details
2023-07-21 14:56:43 -0500 Rating Details
2023-07-21 14:49:09 -0500 Rating Details
2023-07-21 14:44:14 -0500 Rating Details
2023-07-21 14:34:04 -0500 Rating Details
2023-07-21 14:28:00 -0500 Rating Details
2023-07-21 14:23:42 -0500 Rating Details
2023-07-21 14:23:09 -0500 Rating Details
2023-07-21 14:22:56 -0500 Rating Details
2023-07-21 14:17:24 -0500 Rating Details
2023-07-21 14:17:09 -0500 Rating Details
2023-07-21 14:15:59 -0500 Rating Details
2023-07-21 14:02:27 -0500 Rating Details
2023-07-21 13:59:23 -0500 Rating Details
2023-07-21 13:58:18 -0500 Rating Details
2023-07-21 13:57:18 -0500 Rating Details
2023-07-21 13:51:50 -0500 Rating Details
2023-07-21 13:48:11 -0500 Rating Details
2023-07-21 13:47:14 -0500 Rating Details
2023-07-21 13:46:42 -0500 Rating Details
2023-07-21 13:44:56 -0500 Rating Details
2023-07-21 13:40:28 -0500 Rating Details
2023-07-21 13:37:45 -0500 Rating Details
2023-07-21 13:37:35 -0500 Rating Details
2023-07-21 13:37:18 -0500 Rating Details
2023-07-21 13:30:10 -0500 Rating Details
2023-07-21 13:27:18 -0500 Rating Details
2023-07-21 13:25:10 -0500 Rating Details
2023-07-21 13:24:33 -0500 Rating Details
2023-07-21 13:20:34 -0500 Rating Details
2023-07-21 13:18:27 -0500 Rating Details
2023-07-21 13:13:30 -0500 Rating Details
2023-07-21 13:05:01 -0500 Rating Details
2023-07-21 12:58:31 -0500 Rating Details
2023-07-21 12:54:22 -0500 Rating Details
2023-07-21 12:51:21 -0500 Rating Details
2023-07-21 12:51:02 -0500 Rating Details
2023-07-21 12:48:59 -0500 Rating Details
2023-07-21 12:48:53 -0500 Rating Details
2023-07-21 12:47:47 -0500 Rating Details
2023-07-21 12:47:35 -0500 Rating Details
2023-07-21 12:45:58 -0500 Rating Details
2023-07-21 12:45:53 -0500 Rating Details
2023-07-21 12:45:15 -0500 Rating Details
2023-07-21 12:42:37 -0500 Rating Details
2023-07-21 12:38:36 -0500 Rating Details
2023-07-21 12:35:23 -0500 Rating Details
2023-07-21 12:33:09 -0500 Rating Details
2023-07-21 12:25:07 -0500 Rating Details
2023-07-21 12:22:34 -0500 Rating Details
2023-07-21 12:19:40 -0500 Rating Details
2023-07-21 12:18:51 -0500 Rating Details
2023-07-21 12:17:12 -0500 Rating Details
2023-07-21 12:16:00 -0500 Rating Details
2023-07-21 12:10:27 -0500 Rating Details
2023-07-21 12:10:21 -0500 Rating Details
2023-07-21 12:10:05 -0500 Rating Details
2023-07-21 12:09:52 -0500 Rating Details
2023-07-21 12:03:53 -0500 Rating Details
2023-07-21 12:00:25 -0500 Rating Details
2023-07-21 11:59:24 -0500 Rating Details
2023-07-21 11:58:22 -0500 Rating Details
2023-07-21 11:58:13 -0500 Rating Details
2023-07-21 11:51:39 -0500 Rating Details
2023-07-21 11:51:07 -0500 Rating Details
2023-07-21 11:48:50 -0500 Rating Details
2023-07-21 11:48:27 -0500 Rating Details
2023-07-21 11:48:11 -0500 Rating Details
2023-07-21 11:47:24 -0500 Rating Details
2023-07-21 11:47:20 -0500 Rating Details
2023-07-21 11:45:53 -0500 Rating Details
2023-07-21 11:43:00 -0500 Rating Details
2023-07-21 11:39:55 -0500 Rating Details
2023-07-21 11:39:41 -0500 Rating Details
2023-07-21 11:35:37 -0500 Rating Details
2023-07-21 11:34:56 -0500 Rating Details
2023-07-21 11:34:55 -0500 Rating Details
2023-07-21 11:34:43 -0500 Rating Details
2023-07-21 11:31:27 -0500 Rating Details
2023-07-21 11:30:40 -0500 Rating Details
2023-07-21 11:30:35 -0500 Rating Details
2023-07-21 11:29:10 -0500 Rating Details
2023-07-21 11:28:20 -0500 Rating Details
2023-07-21 11:26:10 -0500 Rating Details
2023-07-21 11:19:51 -0500 Rating Details
2023-07-21 11:18:35 -0500 Rating Details
2023-07-21 11:18:31 -0500 Rating Details
2023-07-21 11:16:42 -0500 Rating Details
2023-07-21 11:12:52 -0500 Rating Details
2023-07-21 11:11:41 -0500 Rating Details
2023-07-21 11:10:53 -0500 Rating Details
2023-07-21 11:07:39 -0500 Rating Details
2023-07-21 11:07:32 -0500 Rating Details
2023-07-21 11:03:13 -0500 Rating Details
2023-07-21 11:01:29 -0500 Rating Details
2023-07-21 11:00:52 -0500 Rating Details
2023-07-21 11:00:49 -0500 Rating Details
2023-07-21 10:55:24 -0500 Rating Details
2023-07-21 10:55:13 -0500 Rating Details
2023-07-21 10:54:57 -0500 Rating Details
2023-07-21 10:54:44 -0500 Rating Details
2023-07-21 10:52:46 -0500 Rating Details
2023-07-21 10:51:37 -0500 Rating Details
2023-07-21 10:51:06 -0500 Rating Details
2023-07-21 10:50:42 -0500 Rating Details
2023-07-21 10:49:13 -0500 Rating Details
2023-07-21 10:48:12 -0500 Rating Details
2023-07-21 10:47:35 -0500 Rating Details
2023-07-21 10:47:18 -0500 Rating Details
2023-07-21 10:46:43 -0500 Rating Details
2023-07-21 10:43:57 -0500 Rating Details
2023-07-22 19:24:21 -0500 Rating Details
2023-07-22 18:42:19 -0500 Rating Details
2023-07-22 15:19:50 -0500 Rating Details
2023-07-22 15:02:30 -0500 Rating Details
2023-07-22 13:42:23 -0500 Rating Details
2023-07-22 13:38:46 -0500 Rating Details
2023-07-22 12:26:24 -0500 Rating Details
2023-07-22 12:19:20 -0500 Rating Details
2023-07-22 12:11:17 -0500 Rating Details
2023-07-22 12:05:54 -0500 Rating Details
2023-07-22 11:21:54 -0500 Rating Details
2023-07-22 11:21:36 -0500 Rating Details
2023-07-22 11:14:38 -0500 Rating Details
2023-07-22 10:58:45 -0500 Rating Details
2023-07-22 10:56:54 -0500 Rating Details
2023-07-22 10:07:16 -0500 Rating Details
2023-07-22 09:32:40 -0500 Rating Details
2023-07-22 09:01:20 -0500 Rating Details
2023-07-22 08:45:48 -0500 Rating Details
2023-07-22 08:19:20 -0500 Rating Details
2023-07-22 08:08:04 -0500 Rating Details
2023-07-22 07:49:39 -0500 Rating Details
2023-07-22 07:05:54 -0500 Rating Details
2023-07-22 06:52:50 -0500 Rating Details
2023-07-22 06:08:50 -0500 Rating Details
2023-07-22 05:56:59 -0500 Rating Details
2023-07-22 05:52:40 -0500 Rating Details
2023-07-22 05:36:12 -0500 Rating Details
2023-07-22 05:20:19 -0500 Rating Details
2023-07-22 04:53:21 -0500 Rating Details
2023-07-22 04:47:21 -0500 Rating Details
2023-07-22 04:26:56 -0500 Rating Details
2023-07-22 03:56:00 -0500 Rating Details
2023-07-22 03:23:32 -0500 Rating Details
2023-07-22 02:42:25 -0500 Rating Details
2023-07-22 02:39:49 -0500 Rating Details
2023-07-22 02:39:02 -0500 Rating Details
2023-07-22 01:03:14 -0500 Rating Details
2023-07-22 00:09:32 -0500 Rating Details
2023-07-21 23:22:13 -0500 Rating Details
2023-07-21 23:10:06 -0500 Rating Details
2023-07-21 23:02:55 -0500 Rating Details
2023-07-21 22:31:04 -0500 Rating Details
2023-07-21 22:28:55 -0500 Rating Details
2023-07-21 22:26:53 -0500 Rating Details
2023-07-21 22:26:32 -0500 Rating Details
2023-07-21 21:56:18 -0500 Rating Details
2023-07-21 21:24:21 -0500 Rating Details
2023-07-21 21:19:45 -0500 Rating Details
2023-07-21 21:09:09 -0500 Rating Details
2023-07-21 21:02:54 -0500 Rating Details
2023-07-21 21:01:18 -0500 Rating Details
2023-07-21 20:58:58 -0500 Rating Details
2023-07-21 20:57:05 -0500 Rating Details
2023-07-21 20:49:16 -0500 Rating Details
2023-07-21 20:46:07 -0500 Rating Details
2023-07-21 20:34:31 -0500 Rating Details
2023-07-21 20:33:13 -0500 Rating Details
2023-07-21 20:31:58 -0500 Rating Details
2023-07-21 20:18:00 -0500 Rating Details
2023-07-21 20:15:09 -0500 Rating Details
2023-07-21 20:05:56 -0500 Rating Details
2023-07-21 19:56:27 -0500 Rating Details
2023-07-23 16:50:55 -0500 Rating Details
2023-07-22 21:03:09 -0500 Rating Details
2023-07-22 20:13:44 -0500 Rating Details
2023-08-15 15:25:16 -0500 Rating Details