Viewing enriched Twitter post
Solved it. Tracked down the inference + evaluation bottlenecks and ended up cutting runtime by 3x. GPU throttling was absurdly high. Codex genuinely helped a lot and its capabilities are impressive, but after spending hours pushing both Codex and Claude at their limits, I'm even more convinced they're still far from replacing Honestly the satisfaction I got is just another kind of high **Also got crazy number of impressions, it's always the most low effort tweets
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2056324346009027014/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2056324346009027014/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-05-18T14:33:58.736935",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2056324346009027014",
"url": "https://x.com/Gauri_the_great/status/2056324346009027014",
"twitterUrl": "https://twitter.com/Gauri_the_great/status/2056324346009027014",
"text": "Solved it.\n\nTracked down the inference + evaluation bottlenecks and ended up cutting runtime by 3x. GPU throttling was absurdly high.\n\nCodex genuinely helped a lot and its capabilities are impressive, but after spending hours pushing both Codex and Claude at their limits, I'm even more convinced they're still far from replacing \n\nHonestly the satisfaction I got is just another kind of high \n\n**Also got crazy number of impressions, it's always the most low effort tweets",
"source": "Twitter for iPhone",
"retweetCount": 2,
"replyCount": 2,
"likeCount": 39,
"quoteCount": 0,
"viewCount": 3566,
"createdAt": "Mon May 18 10:41:43 +0000 2026",
"lang": "en",
"bookmarkCount": 12,
"isReply": false,
"inReplyToId": null,
"conversationId": "2056324346009027014",
"displayTextRange": [
0,
276
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "Gauri_the_great",
"url": "https://x.com/Gauri_the_great",
"twitterUrl": "https://twitter.com/Gauri_the_great",
"id": "1641108657948753920",
"name": "Gauri Tripathi",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2003947052775231493/RDmK5fYI_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1641108657948753920/1724954497",
"description": "",
"location": "",
"followers": 3426,
"following": 488,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Mar 29 16:03:05 +0000 2023",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 22545,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 599,
"statusesCount": 3587,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1953880791525540232"
],
"profile_bio": {
"description": "AI Researcher | \nWorking on speech models |\nCreating for the love of it",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "medium.com/@gauritr01",
"expanded_url": "https://medium.com/@gauritr01",
"indices": [
0,
23
],
"url": "https://t.co/Z8nJ2nDtSb"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/adp0f3zK4G",
"expanded_url": "https://twitter.com/Gauri_the_great/status/2056324346009027014/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2056323053173497856",
"indices": [
277,
300
],
"media_key": "3_2056323053173497856",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARyJhuwH2mAACgACHImIGQrbAcYAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHImG7AfaYAAKAAIciYgZCtsBxgAA",
"media_key": "3_2056323053173497856"
}
},
"media_url_https": "https://pbs.twimg.com/media/HImG7AfaYAAfVeE.png",
"original_info": {
"focus_rects": [
{
"h": 266,
"w": 475,
"x": 0,
"y": 0
},
{
"h": 266,
"w": 266,
"x": 0,
"y": 0
},
{
"h": 266,
"w": 233,
"x": 0,
"y": 0
},
{
"h": 266,
"w": 133,
"x": 19,
"y": 0
},
{
"h": 266,
"w": 682,
"x": 0,
"y": 0
}
],
"height": 266,
"width": 682
},
"sizes": {
"large": {
"h": 266,
"w": 682
}
},
"type": "photo",
"url": "https://t.co/adp0f3zK4G"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2055985078162042959",
"url": "https://x.com/Gauri_the_great/status/2055985078162042959",
"twitterUrl": "https://twitter.com/Gauri_the_great/status/2055985078162042959",
"text": "Asked Codex to fix a multi-GPU inference bottleneck.\n\nGPUs were barely utilized, inference was throttling and instead of tracing the pipeline it spent 10 minutes checking whether I had \"Python 2.8 or 2.9\" installed.\n\nThe tendency for coding agents to spiral away from the active bottleneck into irrelevant environment debugging is still a huge problem.",
"source": "Twitter for iPhone",
"retweetCount": 6,
"replyCount": 17,
"likeCount": 147,
"quoteCount": 3,
"viewCount": 32098,
"createdAt": "Sun May 17 12:13:35 +0000 2026",
"lang": "en",
"bookmarkCount": 33,
"isReply": false,
"inReplyToId": null,
"conversationId": "2055985078162042959",
"displayTextRange": [
0,
278
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "Gauri_the_great",
"url": "https://x.com/Gauri_the_great",
"twitterUrl": "https://twitter.com/Gauri_the_great",
"id": "1641108657948753920",
"name": "Gauri Tripathi",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2003947052775231493/RDmK5fYI_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1641108657948753920/1724954497",
"description": "",
"location": "",
"followers": 3426,
"following": 488,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Mar 29 16:03:05 +0000 2023",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 22545,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 599,
"statusesCount": 3587,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1953880791525540232"
],
"profile_bio": {
"description": "AI Researcher | \nWorking on speech models |\nCreating for the love of it",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "medium.com/@gauritr01",
"expanded_url": "https://medium.com/@gauritr01",
"indices": [
0,
23
],
"url": "https://t.co/Z8nJ2nDtSb"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2053897598260703646",
"url": "",
"twitterUrl": "",
"text": "",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 0,
"likeCount": 0,
"quoteCount": 0,
"viewCount": 0,
"createdAt": "",
"lang": "",
"bookmarkCount": 0,
"isReply": false,
"inReplyToId": null,
"conversationId": "",
"displayTextRange": [],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}