Viewing enriched Twitter post
@giffmana @ChengleiSi It’s a commit that lowered val loss but *increased* the wall clock time so it gets rejected for being slower. must improve one, the other or both in this version. In my (new) autoresearch repo I have an alternative approach where you *always* train for eg 5 minutes and try to reduce val loss as much as possible. Possibly less confusing but has its own issues too.
{
"score": 0.38,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.08000000000000002,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-03-07T07:24:39.802769",
"import_source": "api_import",
"source_tagged_at": "2026-03-07T07:24:39.802795",
"enriched": true,
"enriched_at": "2026-03-07T07:24:39.802800"
}{
"type": "tweet",
"id": "2030219327459225650",
"url": "https://x.com/karpathy/status/2030219327459225650",
"twitterUrl": "https://twitter.com/karpathy/status/2030219327459225650",
"text": "@giffmana @ChengleiSi It’s a commit that lowered val loss but *increased* the wall clock time so it gets rejected for being slower. must improve one, the other or both in this version. In my (new) autoresearch repo I have an alternative approach where you *always* train for eg 5 minutes and try to reduce val loss as much as possible. Possibly less confusing but has its own issues too.",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 2,
"likeCount": 25,
"quoteCount": 0,
"viewCount": 2790,
"createdAt": "Sat Mar 07 09:49:41 +0000 2026",
"lang": "en",
"bookmarkCount": 7,
"isReply": true,
"inReplyToId": "2030199507162431612",
"conversationId": "2029701092347630069",
"displayTextRange": [
22,
298
],
"inReplyToUserId": "2236047510",
"inReplyToUsername": "giffmana",
"author": {
"type": "user",
"userName": "karpathy",
"url": "https://x.com/karpathy",
"twitterUrl": "https://twitter.com/karpathy",
"id": "33836629",
"name": "Andrej Karpathy",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1296667294148382721/9Pr6XrPB_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/33836629/1407117611",
"description": "",
"location": "Stanford",
"followers": 1890969,
"following": 1055,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Apr 21 06:49:15 +0000 2009",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 22237,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 854,
"statusesCount": 9991,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1617979122625712128"
],
"profile_bio": {
"description": "I like to train large deep neural nets. Previously Director of AI @ Tesla, founding team @ OpenAI, PhD @ Stanford.",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"url": {
"urls": [
{
"display_url": "karpathy.ai",
"expanded_url": "https://karpathy.ai",
"indices": [
0,
23
],
"url": "https://t.co/0EcFthjJXM"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}