@arankomatsuzaki
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback Overviews techniques to understand, improve, and complement RLHF in practice https://t.co/pBX2mAqd1C https://t.co/KTDaKXmj4f
Viewing enriched Twitter post
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback Overviews techniques to understand, improve, and complement RLHF in practice https://t.co/pBX2mAqd1C https://t.co/KTDaKXmj4f
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1685813753063870465/media_0.png",
"type": "photo",
"original_url": "http://pbs.twimg.com/media/F2U2b2_XUAIMyoI.png",
"download_date": "2025-08-13T05:53:10.332131",
"stored_in_supabase": true,
"format_converted_from_list": true
}
],
"conversion_date": "2025-08-13T00:32:38.524169",
"format_converted": true,
"original_structure": "had_media_only"
} {
"created_at": "Mon Jul 31 00:44:54 +0000 2023",
"id": 1685813753063870465,
"id_str": "1685813753063870465",
"full_text": "Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback\n\nOverviews techniques to understand, improve, and complement RLHF in practice\n\nhttps://t.co/pBX2mAqd1C https://t.co/KTDaKXmj4f",
"truncated": false,
"display_text_range": [
0,
190
],
"entities": {
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [
{
"url": "https://t.co/pBX2mAqd1C",
"expanded_url": "https://arxiv.org/abs/2307.15217",
"display_url": "arxiv.org/abs/2307.15217",
"indices": [
167,
190
]
}
],
"media": [
{
"id": 1685813487765770242,
"id_str": "1685813487765770242",
"indices": [
191,
214
],
"media_url": "http://pbs.twimg.com/media/F2U2b2_XUAIMyoI.png",
"media_url_https": "https://pbs.twimg.com/media/F2U2b2_XUAIMyoI.png",
"url": "https://t.co/KTDaKXmj4f",
"display_url": "pic.twitter.com/KTDaKXmj4f",
"expanded_url": "https://twitter.com/arankomatsuzaki/status/1685813753063870465/photo/1",
"type": "photo",
"sizes": {
"small": {
"w": 672,
"h": 680,
"resize": "fit"
},
"large": {
"w": 864,
"h": 874,
"resize": "fit"
},
"medium": {
"w": 864,
"h": 874,
"resize": "fit"
},
"thumb": {
"w": 150,
"h": 150,
"resize": "crop"
}
}
}
]
},
"extended_entities": {
"media": [
{
"id": 1685813487765770242,
"id_str": "1685813487765770242",
"indices": [
191,
214
],
"media_url": "http://pbs.twimg.com/media/F2U2b2_XUAIMyoI.png",
"media_url_https": "https://pbs.twimg.com/media/F2U2b2_XUAIMyoI.png",
"url": "https://t.co/KTDaKXmj4f",
"display_url": "pic.twitter.com/KTDaKXmj4f",
"expanded_url": "https://twitter.com/arankomatsuzaki/status/1685813753063870465/photo/1",
"type": "photo",
"sizes": {
"small": {
"w": 672,
"h": 680,
"resize": "fit"
},
"large": {
"w": 864,
"h": 874,
"resize": "fit"
},
"medium": {
"w": 864,
"h": 874,
"resize": "fit"
},
"thumb": {
"w": 150,
"h": 150,
"resize": "crop"
}
}
}
]
},
"source": "<a href=\"https://mobile.twitter.com\" rel=\"nofollow\">Twitter Web App</a>",
"in_reply_to_status_id": null,
"in_reply_to_status_id_str": null,
"in_reply_to_user_id": null,
"in_reply_to_user_id_str": null,
"in_reply_to_screen_name": null,
"user": {
"id": 794433401591693312,
"id_str": "794433401591693312",
"name": "Aran Komatsuzaki",
"screen_name": "arankomatsuzaki",
"location": "",
"description": "ML PhD @ GaTech, @TheDuckAI, EleutherAI, LAION.",
"url": "https://t.co/aZGCShnLYq",
"entities": {
"url": {
"urls": [
{
"url": "https://t.co/aZGCShnLYq",
"expanded_url": "https://arankomatsuzaki.wordpress.com/about-me/",
"display_url": "arankomatsuzaki.wordpress.com/about-me/",
"indices": [
0,
23
]
}
]
},
"description": {
"urls": []
}
},
"protected": false,
"followers_count": 63287,
"friends_count": 76,
"listed_count": 934,
"created_at": "Fri Nov 04 06:57:37 +0000 2016",
"favourites_count": 8475,
"utc_offset": null,
"time_zone": null,
"geo_enabled": false,
"verified": false,
"statuses_count": 3686,
"lang": null,
"contributors_enabled": false,
"is_translator": false,
"is_translation_enabled": false,
"profile_background_color": "F5F8FA",
"profile_background_image_url": null,
"profile_background_image_url_https": null,
"profile_background_tile": false,
"profile_image_url": "http://pbs.twimg.com/profile_images/1561220982328754176/JOYS5kab_normal.jpg",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1561220982328754176/JOYS5kab_normal.jpg",
"profile_link_color": "1DA1F2",
"profile_sidebar_border_color": "C0DEED",
"profile_sidebar_fill_color": "DDEEF6",
"profile_text_color": "333333",
"profile_use_background_image": true,
"has_extended_profile": false,
"default_profile": true,
"default_profile_image": false,
"following": true,
"follow_request_sent": false,
"notifications": false,
"translator_type": "none",
"withheld_in_countries": []
},
"geo": null,
"coordinates": null,
"place": null,
"contributors": null,
"is_quote_status": false,
"retweet_count": 122,
"favorite_count": 525,
"favorited": false,
"retweeted": false,
"possibly_sensitive": false,
"possibly_sensitive_appealable": false,
"lang": "en"
}