Viewing enriched Twitter post
Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods "This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models on challenging reasoning tasks." "Non-reasoning models… https://t.co/g8tqp3whNQ
{
"media": [
{
"type": "image",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1914630337373913332/media_0.jpg?",
"filename": "media_0.jpg"
}
],
"nlp": {
"sentiment": "neutral",
"topics": [
"inference-time scaling",
"reasoning models",
"efficiency analysis"
],
"entities": [],
"summary": "The tweet discusses a comprehensive analysis of inference-time scaling methods for reasoning and non-reasoning models.",
"language": "en",
"processed_at": "2025-08-07T12:12:44.864061"
}
}{
"data": {
"threaded_conversation_with_injections_v2": {
"instructions": [
{
"type": "TimelineClearCache"
},
{
"type": "TimelineAddEntries",
"entries": [
{
"entryId": "tweet-1914630337373913332",
"sortIndex": "1953519669130297344",
"content": {
"entryType": "TimelineTimelineItem",
"__typename": "TimelineTimelineItem",
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914630337373913332",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjo0NDE0NjU3NTE=",
"rest_id": "441465751",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": true,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": true,
"can_media_tag": true,
"created_at": "Tue Dec 20 03:45:50 +0000 2011",
"default_profile": false,
"default_profile_image": false,
"description": "CEO @SophontAI |\nPhD at 19 (2023) |\nFounder, ex CEO @MedARC_AI |\nex Research Director Stability AI | \nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/xPxwKTq6Qb",
"entities": {
"description": {
"urls": [
{
"display_url": "bit.ly/3tpAuan",
"expanded_url": "https://bit.ly/3tpAuan",
"url": "https://t.co/xPxwKTq6Qb",
"indices": [
136,
159
]
}
]
},
"url": {
"urls": [
{
"display_url": "sophontai.com",
"expanded_url": "https://sophontai.com",
"url": "https://t.co/uQ936JTZf1",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 104329,
"followers_count": 79718,
"friends_count": 1237,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1178,
"location": "",
"media_count": 2411,
"name": "Tanishq Mathew Abraham, Ph.D.",
"normal_followers_count": 79718,
"pinned_tweet_ids_str": [
"1952221233648718307"
],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/441465751/1738204246",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1913710019729821696/Qge4zx6u_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "iScienceLuvr",
"statuses_count": 17695,
"translator_type": "none",
"url": "https://t.co/uQ936JTZf1",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"professional": {
"rest_id": "1534109693131362304",
"professional_type": "Creator",
"category": [
{
"id": 713,
"name": "Science & Technology",
"icon_name": ""
}
]
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1914630337373913332"
],
"editable_until_msecs": "1745322019000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "17770",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://mobile.twitter.com\" rel=\"nofollow\">Twitter Web App</a>",
"note_tweet": {
"is_expandable": true,
"note_tweet_results": {
"result": {
"id": "Tm90ZVR3ZWV0OjE5MTQ2MzAzMzcyNzMxOTI0NDk=",
"text": "Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods\n\n\"This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models on challenging reasoning tasks.\"\n\n\"Non-reasoning models augmented by inference-time methods cannot match reasoning models\"\n\n\"Majority voting is often the best inference-time scaling method – for both reasoning and non-reasoning\"\n\n\"For reasoning models, shorter responses are more likely to be correct\"",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 169,
"bookmarked": false,
"created_at": "Tue Apr 22 10:40:19 +0000 2025",
"conversation_id_str": "1914630337373913332",
"display_text_range": [
0,
277
],
"entities": {
"hashtags": [],
"media": [
{
"display_url": "pic.x.com/g8tqp3whNQ",
"expanded_url": "https://x.com/iScienceLuvr/status/1914630337373913332/photo/1",
"id_str": "1914629868807184384",
"indices": [
278,
301
],
"media_key": "3_1914629868807184384",
"media_url_https": "https://pbs.twimg.com/media/GpIhuLaa4AANUkA.jpg",
"type": "photo",
"url": "https://t.co/g8tqp3whNQ",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 1815,
"w": 1400,
"resize": "fit"
},
"medium": {
"h": 1200,
"w": 926,
"resize": "fit"
},
"small": {
"h": 680,
"w": 525,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 1815,
"width": 1400,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1400,
"h": 784
},
{
"x": 0,
"y": 0,
"w": 1400,
"h": 1400
},
{
"x": 0,
"y": 0,
"w": 1400,
"h": 1596
},
{
"x": 0,
"y": 0,
"w": 908,
"h": 1815
},
{
"x": 0,
"y": 0,
"w": 1400,
"h": 1815
}
]
},
"allow_download_status": {
"allow_download": true
},
"media_results": {
"result": {
"media_key": "3_1914629868807184384"
}
}
}
],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"extended_entities": {
"media": [
{
"display_url": "pic.x.com/g8tqp3whNQ",
"expanded_url": "https://x.com/iScienceLuvr/status/1914630337373913332/photo/1",
"id_str": "1914629868807184384",
"indices": [
278,
301
],
"media_key": "3_1914629868807184384",
"media_url_https": "https://pbs.twimg.com/media/GpIhuLaa4AANUkA.jpg",
"type": "photo",
"url": "https://t.co/g8tqp3whNQ",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": []
},
"medium": {
"faces": []
},
"small": {
"faces": []
},
"orig": {
"faces": []
}
},
"sizes": {
"large": {
"h": 1815,
"w": 1400,
"resize": "fit"
},
"medium": {
"h": 1200,
"w": 926,
"resize": "fit"
},
"small": {
"h": 680,
"w": 525,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 1815,
"width": 1400,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1400,
"h": 784
},
{
"x": 0,
"y": 0,
"w": 1400,
"h": 1400
},
{
"x": 0,
"y": 0,
"w": 1400,
"h": 1596
},
{
"x": 0,
"y": 0,
"w": 908,
"h": 1815
},
{
"x": 0,
"y": 0,
"w": 1400,
"h": 1815
}
]
},
"allow_download_status": {
"allow_download": true
},
"media_results": {
"result": {
"media_key": "3_1914629868807184384"
}
}
}
]
},
"favorite_count": 215,
"favorited": false,
"full_text": "Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods\n\n\"This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models on challenging reasoning tasks.\"\n\n\"Non-reasoning models… https://t.co/g8tqp3whNQ",
"is_quote_status": false,
"lang": "en",
"possibly_sensitive": false,
"possibly_sensitive_editable": true,
"quote_count": 0,
"reply_count": 2,
"retweet_count": 37,
"retweeted": false,
"user_id_str": "441465751",
"id_str": "1914630337373913332"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "SelfThread"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet"
}
}
},
{
"entryId": "conversationthread-1914630339286458389",
"sortIndex": "1953519669130297334",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1914630339286458389-tweet-1914630339286458389",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1914630339286458389",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjo0NDE0NjU3NTE=",
"rest_id": "441465751",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": true,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": true,
"can_media_tag": true,
"created_at": "Tue Dec 20 03:45:50 +0000 2011",
"default_profile": false,
"default_profile_image": false,
"description": "CEO @SophontAI |\nPhD at 19 (2023) |\nFounder, ex CEO @MedARC_AI |\nex Research Director Stability AI | \nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/xPxwKTq6Qb",
"entities": {
"description": {
"urls": [
{
"display_url": "bit.ly/3tpAuan",
"expanded_url": "https://bit.ly/3tpAuan",
"url": "https://t.co/xPxwKTq6Qb",
"indices": [
136,
159
]
}
]
},
"url": {
"urls": [
{
"display_url": "sophontai.com",
"expanded_url": "https://sophontai.com",
"url": "https://t.co/uQ936JTZf1",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 104329,
"followers_count": 79718,
"friends_count": 1237,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1178,
"location": "",
"media_count": 2411,
"name": "Tanishq Mathew Abraham, Ph.D.",
"normal_followers_count": 79718,
"pinned_tweet_ids_str": [
"1952221233648718307"
],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/441465751/1738204246",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1913710019729821696/Qge4zx6u_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "iScienceLuvr",
"statuses_count": 17695,
"translator_type": "none",
"url": "https://t.co/uQ936JTZf1",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"professional": {
"rest_id": "1534109693131362304",
"professional_type": "Creator",
"category": [
{
"id": 713,
"name": "Science & Technology",
"icon_name": ""
}
]
},
"tipjar_settings": {}
}
}
},
"card": {
"rest_id": "https://t.co/yquFHlKsci",
"legacy": {
"binding_values": [
{
"key": "thumbnail_image",
"value": {
"image_value": {
"alt": "arXiv logo",
"height": 144,
"width": 144,
"url": "https://pbs.twimg.com/card_img/1952295676374810624/xxWiRL_6?format=jpg&name=144x144_2"
},
"type": "IMAGE"
}
},
{
"key": "description",
"value": {
"string_value": "There is intense interest in investigating how inference time compute (ITC) (e.g. repeated sampling, refinements, etc) can improve large language model (LLM) capabilities. At the same time, recent...",
"type": "STRING"
}
},
{
"key": "domain",
"value": {
"string_value": "arxiv.org",
"type": "STRING"
}
},
{
"key": "thumbnail_image_large",
"value": {
"image_value": {
"alt": "arXiv logo",
"height": 420,
"width": 420,
"url": "https://pbs.twimg.com/card_img/1952295676374810624/xxWiRL_6?format=jpg&name=420x420_2"
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image_original",
"value": {
"image_value": {
"alt": "arXiv logo",
"height": 1000,
"width": 1000,
"url": "https://pbs.twimg.com/card_img/1952295676374810624/xxWiRL_6?format=jpg&name=orig"
},
"type": "IMAGE"
}
},
{
"key": "site",
"value": {
"scribe_key": "publisher_id",
"type": "USER",
"user_value": {
"id_str": "808633423300624384",
"path": []
}
}
},
{
"key": "thumbnail_image_small",
"value": {
"image_value": {
"alt": "arXiv logo",
"height": 100,
"width": 100,
"url": "https://pbs.twimg.com/card_img/1952295676374810624/xxWiRL_6?format=jpg&name=100x100_2"
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image_x_large",
"value": {
"image_value": {
"alt": "arXiv logo",
"height": 1000,
"width": 1000,
"url": "https://pbs.twimg.com/card_img/1952295676374810624/xxWiRL_6?format=png&name=2048x2048_2_exp"
},
"type": "IMAGE"
}
},
{
"key": "thumbnail_image_alt_text",
"value": {
"string_value": "arXiv logo",
"type": "STRING"
}
},
{
"key": "vanity_url",
"value": {
"scribe_key": "vanity_url",
"string_value": "arxiv.org",
"type": "STRING"
}
},
{
"key": "thumbnail_image_color",
"value": {
"image_color_value": {
"palette": [
{
"rgb": {
"blue": 255,
"green": 255,
"red": 255
},
"percentage": 94.17
},
{
"rgb": {
"blue": 105,
"green": 116,
"red": 124
},
"percentage": 4.33
},
{
"rgb": {
"blue": 46,
"green": 21,
"red": 170
},
"percentage": 1.26
},
{
"rgb": {
"blue": 131,
"green": 116,
"red": 203
},
"percentage": 0.23
}
]
},
"type": "IMAGE_COLOR"
}
},
{
"key": "title",
"value": {
"string_value": "Think Deep, Think Fast: Investigating Efficiency of Verifier-free...",
"type": "STRING"
}
},
{
"key": "card_url",
"value": {
"scribe_key": "card_url",
"string_value": "https://t.co/yquFHlKsci",
"type": "STRING"
}
}
],
"card_platform": {
"platform": {
"audience": {
"name": "production"
},
"device": {
"name": "Android",
"version": "12"
}
}
},
"name": "summary",
"url": "https://t.co/yquFHlKsci",
"user_refs_results": [
{
"result": {
"__typename": "User",
"id": "VXNlcjo4MDg2MzM0MjMzMDA2MjQzODQ=",
"rest_id": "808633423300624384",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": false,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": true,
"can_media_tag": true,
"created_at": "Tue Dec 13 11:23:26 +0000 2016",
"default_profile": false,
"default_profile_image": false,
"description": "News from https://t.co/enurGFxpcS, a free distribution service and an open archive for scholarly articles.\n\nFor help with arXiv, see https://t.co/LcWuhM0BOl",
"entities": {
"description": {
"urls": [
{
"display_url": "arXiv.org",
"expanded_url": "http://arXiv.org",
"url": "https://t.co/enurGFxpcS",
"indices": [
10,
33
]
},
{
"display_url": "arxiv.org/help",
"expanded_url": "https://arxiv.org/help",
"url": "https://t.co/LcWuhM0BOl",
"indices": [
133,
156
]
}
]
},
"url": {
"urls": [
{
"display_url": "arxiv.org",
"expanded_url": "https://arxiv.org/",
"url": "https://t.co/DHMkdi4lF9",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 948,
"followers_count": 41367,
"friends_count": 187,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 487,
"location": "Ithaca, NY",
"media_count": 109,
"name": "arXiv.org",
"normal_followers_count": 41367,
"pinned_tweet_ids_str": [],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/808633423300624384/1481635469",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1365352170267299840/IzvjKckL_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "arxiv",
"statuses_count": 1106,
"translator_type": "none",
"url": "https://t.co/DHMkdi4lF9",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
]
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1914630339286458389"
],
"editable_until_msecs": "1745322019000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "2310",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://mobile.twitter.com\" rel=\"nofollow\">Twitter Web App</a>",
"legacy": {
"bookmark_count": 6,
"bookmarked": false,
"created_at": "Tue Apr 22 10:40:19 +0000 2025",
"conversation_id_str": "1914630337373913332",
"display_text_range": [
0,
28
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "arxiv.org/abs/2504.14047",
"expanded_url": "https://arxiv.org/abs/2504.14047",
"url": "https://t.co/yquFHlKsci",
"indices": [
5,
28
]
}
],
"user_mentions": []
},
"favorite_count": 12,
"favorited": false,
"full_text": "abs: https://t.co/yquFHlKsci",
"in_reply_to_screen_name": "iScienceLuvr",
"in_reply_to_status_id_str": "1914630337373913332",
"in_reply_to_user_id_str": "441465751",
"is_quote_status": false,
"lang": "und",
"possibly_sensitive": false,
"possibly_sensitive_editable": true,
"quote_count": 0,
"reply_count": 0,
"retweet_count": 0,
"retweeted": false,
"user_id_str": "441465751",
"id_str": "1914630339286458389"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "SelfThread"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1914630339286458389"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "conversationthread-1919500965130207562",
"sortIndex": "1953519669130297324",
"content": {
"entryType": "TimelineTimelineModule",
"__typename": "TimelineTimelineModule",
"items": [
{
"entryId": "conversationthread-1919500965130207562-tweet-1919500965130207562",
"item": {
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1919500965130207562",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxNTc2ODk4MTI3MzY1MzAwMjI0",
"rest_id": "1576898127365300224",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": true,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": false,
"can_media_tag": true,
"created_at": "Mon Oct 03 11:33:13 +0000 2022",
"default_profile": true,
"default_profile_image": false,
"description": "\"A business exists to create value, not jobs. In the process of creating value, it might or might not create jobs.\" Haydar . AI & IoT technologist",
"entities": {
"description": {
"urls": []
}
},
"fast_followers_count": 0,
"favourites_count": 64,
"followers_count": 43,
"friends_count": 187,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 0,
"location": "",
"media_count": 10,
"name": "Haydar Jawad",
"normal_followers_count": 43,
"pinned_tweet_ids_str": [],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/1576898127365300224/1665332789",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1579145059743694848/A1RuOKFO_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "Haydar_A_Jawad",
"statuses_count": 147,
"translator_type": "none",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"professional": {
"rest_id": "1639568496832004096",
"professional_type": "Creator",
"category": [
{
"id": 713,
"name": "Science & Technology",
"icon_name": ""
}
]
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1919500965130207562"
],
"editable_until_msecs": "1746483267000",
"is_edit_eligible": false,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "21",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://mobile.twitter.com\" rel=\"nofollow\">Twitter Web App</a>",
"note_tweet": {
"is_expandable": true,
"note_tweet_results": {
"result": {
"id": "Tm90ZVR3ZWV0OjE5MTk1MDA5NjUwMTI3NjY3MjA=",
"text": "This paper is a masterclass in overstated minimalism, trading on the Stanford name to rebrand a simple supervised fine tuning loop as “autonomous self-improvement.”\n\nThey prompt small models, discard all incorrect answers using a ground-truth answer key (supervised learning), and retrain only on the correct ones. This is label dependent fine tuning masquerading as autonomy.\n\nThey claim that “performance plateaus after increasing dataset size”, of course it does. They are training on synthetic data with limited diversity and aggressive pruning. This demonstrates the limitations of their approach, yet they conveniently bury that fact.\n\nAs for autonomou learning, In proper RL with self play (e.g. AlphaGo), models learn by interacting in a simulated environment and improving through feedback loops they do not predefine.\n\nIn this paper, all the feedback (ground truth) is externally determined, the model is never allowed to decide what \"good\" looks like unless it exactly matches a human written string, thats absolutely Not “autonomous self improvement.”",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": []
},
"richtext": {
"richtext_tags": []
},
"media": {
"inline_media": []
}
}
}
},
"legacy": {
"bookmark_count": 0,
"bookmarked": false,
"created_at": "Mon May 05 21:14:27 +0000 2025",
"conversation_id_str": "1914630337373913332",
"display_text_range": [
14,
295
],
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "441465751",
"name": "Tanishq Mathew Abraham, Ph.D.",
"screen_name": "iScienceLuvr",
"indices": [
0,
13
]
}
]
},
"favorite_count": 0,
"favorited": false,
"full_text": "@iScienceLuvr This paper is a masterclass in overstated minimalism, trading on the Stanford name to rebrand a simple supervised fine tuning loop as “autonomous self-improvement.”\n\nThey prompt small models, discard all incorrect answers using a ground-truth answer key (supervised learning), and…",
"in_reply_to_screen_name": "iScienceLuvr",
"in_reply_to_status_id_str": "1914630337373913332",
"in_reply_to_user_id_str": "441465751",
"is_quote_status": false,
"lang": "en",
"quote_count": 0,
"reply_count": 0,
"retweet_count": 0,
"retweeted": false,
"user_id_str": "1576898127365300224",
"id_str": "1919500965130207562"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
}
],
"metadata": {
"conversationMetadata": {
"allTweetIds": [
"1919500965130207562"
],
"enableDeduplication": true
}
},
"displayType": "VerticalConversation",
"clientEventInfo": {
"component": "tweet",
"details": {
"conversationDetails": {
"conversationSection": "HighQuality"
},
"timelinesDetails": {
"controllerData": "DAACDAAEDAABCgABAAAAAAAAAAEKAAIAAAAAAAAAAAAAAAA="
}
}
}
}
},
{
"entryId": "cursor-bottom-1953519669130297323",
"sortIndex": "1953519669130297323",
"content": {
"entryType": "TimelineTimelineCursor",
"__typename": "TimelineTimelineCursor",
"value": "DAAFCgABGxxLyfQ__-kLAAIAAAA8RW1QQzZ3QUFBZlEvZ0dKTjB2R3AvQUFBQUFNYWtpSWx6MXZBOUJxU0lpWkJXdUFWR3FOdjlUU2JBVW89CAADAAAAAgAA",
"cursorType": "Bottom"
}
}
]
},
{
"type": "TimelineTerminateTimeline",
"direction": "Top"
},
{
"type": "TimelineTerminateTimeline",
"direction": "Bottom"
}
],
"metadata": {
"reader_mode_config": {
"is_reader_mode_available": true
},
"scribeConfig": {
"page": "ranked_replies"
}
}
}
}
}