Viewing enriched Twitter post
Today's YouTube video is a longer look at MoA in Hermes Agent, trying to answer some of the common questions: How does using MoA impact cost, speed, and quality? I created an open weights MoA using GLM-5.2, Kimi K2.6 and Minimax M3 to find out, then made a three-headed Grok with GPT-5.5 as the aggregator to see if that added some much-needed style to the GPT model. Check it out! https://t.co/lQMfbuI1Ix
{
"score": 0.42,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.12000000000000002,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-06-29T20:02:31.676462",
"import_source": "api_import",
"source_tagged_at": "2026-06-29T20:02:31.676473",
"enriched": true,
"enriched_at": "2026-06-29T20:02:31.676476"
}{
"type": "tweet",
"id": "2071595794147250540",
"url": "https://x.com/tonbistudio/status/2071595794147250540",
"twitterUrl": "https://twitter.com/tonbistudio/status/2071595794147250540",
"text": "Today's YouTube video is a longer look at MoA in Hermes Agent, trying to answer some of the common questions: \n\nHow does using MoA impact cost, speed, and quality? \n\nI created an open weights MoA using GLM-5.2, Kimi K2.6 and Minimax M3 to find out, then made a three-headed Grok with GPT-5.5 as the aggregator to see if that added some much-needed style to the GPT model. Check it out!\n\nhttps://t.co/lQMfbuI1Ix",
"source": "Twitter for iPhone",
"retweetCount": 14,
"replyCount": 15,
"likeCount": 174,
"quoteCount": 3,
"viewCount": 20711,
"createdAt": "Mon Jun 29 14:05:00 +0000 2026",
"lang": "en",
"bookmarkCount": 132,
"isReply": false,
"inReplyToId": null,
"conversationId": "2071595794147250540",
"displayTextRange": [
0,
278
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "tonbistudio",
"url": "https://x.com/tonbistudio",
"twitterUrl": "https://twitter.com/tonbistudio",
"id": "1449072997965307906",
"name": "tonbi",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2019464555844562944/y1VHgOeE_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1449072997965307906/1779265381",
"description": "",
"location": "",
"followers": 6421,
"following": 1734,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Fri Oct 15 18:01:54 +0000 2021",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 6949,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 994,
"statusesCount": 3524,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2065561010333962617"
],
"profile_bio": {
"description": "Once described as the \"Bob Ross of AI tutorials\"\nTrying to make agents and AI actually useful for everyone on Tonbi's AI Garage",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "youtube.com/@TonbisAIGarage",
"expanded_url": "http://youtube.com/@TonbisAIGarage",
"indices": [
0,
23
],
"url": "https://t.co/cjQgGYSkBG"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": {
"binding_values": [
{
"key": "player_url",
"value": {
"string_value": "https://www.youtube.com/embed/YAejFePoG8M"
}
},
{
"key": "player_image_large",
"value": {
"image_value": {
"height": 320,
"url": "https://pbs.twimg.com/card_img/2071571576936415232/BTOaHAfv?format=jpg&name=800x320_1",
"width": 569
}
}
},
{
"key": "player_image",
"value": {
"image_value": {
"height": 158,
"url": "https://pbs.twimg.com/card_img/2071571576936415232/BTOaHAfv?format=jpg&name=280x280",
"width": 280
}
}
},
{
"key": "app_star_rating",
"value": {
"string_value": "4.67091"
}
},
{
"key": "description",
"value": {
"string_value": "Nous Research's new Mixture of Agents combines several models into ..."
}
},
{
"key": "player_width",
"value": {
"string_value": "1280"
}
},
{
"key": "domain",
"value": {
"string_value": "www.youtube.com"
}
},
{
"key": "app_is_free",
"value": {
"string_value": "true"
}
},
{
"key": "site",
"value": {
"scribe_key": "publisher_id",
"user_value": {
"id_str": "10228272",
"path": []
}
}
},
{
"key": "player_image_original",
"value": {
"image_value": {
"height": 720,
"url": "https://pbs.twimg.com/card_img/2071571576936415232/BTOaHAfv?format=jpg&name=orig",
"width": 1280
}
}
},
{
"key": "app_url_resolved",
"value": {
"string_value": "vnd.youtube://www.youtube.com/watch?si=IJuij2xubcfdDnRl&v=YAejFePoG8M&feature=youtu.be&feature=applinks"
}
},
{
"key": "app_num_ratings",
"value": {
"string_value": "47,850,326"
}
},
{
"key": "app_price_amount",
"value": {
"string_value": "0.0"
}
},
{
"key": "player_height",
"value": {
"string_value": "720"
}
},
{
"key": "vanity_url",
"value": {
"scribe_key": "vanity_url",
"string_value": "youtube.com"
}
},
{
"key": "app_name",
"value": {
"string_value": "YouTube"
}
},
{
"key": "app_id",
"value": {
"scribe_key": "publisher_app_id",
"string_value": "544007664"
}
},
{
"key": "player_image_small",
"value": {
"image_value": {
"height": 81,
"url": "https://pbs.twimg.com/card_img/2071571576936415232/BTOaHAfv?format=jpg&name=144x144",
"width": 144
}
}
},
{
"key": "title",
"value": {
"string_value": "Creating a New Fable? Testing Mixture of Agents in Hermes Agent"
}
},
{
"key": "app_price_currency",
"value": {
"string_value": "USD"
}
},
{
"key": "app_url",
"value": {
"string_value": "https://t.co/redirect?url=vnd.youtube%3A%2F%2Fwww.youtube.com%2Fwatch%3Fsi%3DIJuij2xubcfdDnRl%26v%3DYAejFePoG8M%26feature%3Dyoutu.be%26feature%3Dapplinks&sig=c3705d7e6fd9a736a1716598add8594bb5deccc2&ssr=true&slug=lQMfbuI1Ix"
}
},
{
"key": "card_url",
"value": {
"scribe_key": "card_url",
"string_value": "https://t.co/lQMfbuI1Ix"
}
},
{
"key": "player_image_color",
"value": {
"image_color_value": {
"palette": [
{
"percentage": 40.83,
"rgb": {
"blue": 14,
"green": 7,
"red": 4
}
},
{
"percentage": 8.4,
"rgb": {
"blue": 5,
"green": 194,
"red": 248
}
},
{
"percentage": 6.27,
"rgb": {
"blue": 63,
"green": 27,
"red": 7
}
},
{
"percentage": 4.58,
"rgb": {
"blue": 201,
"green": 201,
"red": 201
}
},
{
"percentage": 3.87,
"rgb": {
"blue": 21,
"green": 19,
"red": 53
}
}
]
}
}
},
{
"key": "player_image_x_large",
"value": {
"image_value": {
"height": 720,
"url": "https://pbs.twimg.com/card_img/2071571576936415232/BTOaHAfv?format=png&name=2048x2048_2_exp",
"width": 1280
}
}
}
],
"card_platform": {
"platform": {
"audience": {
"name": "production"
},
"device": {
"name": "iPhone",
"version": "13"
}
}
},
"name": "player",
"url": "https://t.co/lQMfbuI1Ix",
"user_refs_results": [
{
"rest_id": "10228272",
"result": {
"__typename": "User",
"action_counts": {
"favorites_count": 6027
},
"avatar": {
"image_url": "https://pbs.twimg.com/profile_images/1984471345854566400/5pd8GpgC_normal.jpg"
},
"banner": {
"image_url": "https://pbs.twimg.com/profile_banners/10228272/1773248035"
},
"core": {
"created_at": "Tue Nov 13 21:43:46 +0000 2007",
"name": "YouTube",
"screen_name": "YouTube"
},
"dm_permissions": {
"can_dm": false
},
"exclusive_tweet_following": false,
"follow_request_sent": false,
"identity_profile_labels_highlighted_label": {},
"location": {
"location": "San Bruno, CA"
},
"media_permissions": {
"can_media_tag": true
},
"notifications_settings": {
"notifications_enabled": false
},
"pinned_items": {
"tweet_ids_str": [
"2064694071537352925"
]
},
"privacy": {
"protected": false,
"suspended": false
},
"private_super_following": false,
"profile_bio": {
"description": "score & subscribe",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "youtube.com",
"expanded_url": "http://youtube.com/",
"indices": [
0,
23
],
"url": "https://t.co/GIOK0JwI68"
}
]
}
}
},
"profile_image_shape": "Square",
"profile_metadata": {
"profile_interstitial_type": "",
"profile_link_color": "C9191D"
},
"profile_translation": {
"translator_type_enum": "Regular"
},
"properties": {
"has_extended_profile": false,
"has_no_screen_name": false
},
"relationship_counts": {
"followers": 68664193,
"following": 1144
},
"relationship_perspectives": {
"blocked_by": false,
"blocking": false,
"followed_by": false,
"following": false,
"live_following": false,
"muting": false
},
"rest_id": "10228272",
"smart_blocked_by": false,
"smart_blocking": false,
"super_follow_eligible": false,
"super_followed_by": false,
"super_following": false,
"tweet_counts": {
"media_tweets": 16148,
"tweets": 61206
},
"verification": {
"is_blue_verified": true,
"verified": false,
"verified_type": "Business"
},
"website": {
"url": "https://t.co/GIOK0JwI68"
}
}
}
]
},
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "youtu.be/YAejFePoG8M",
"expanded_url": "https://youtu.be/YAejFePoG8M",
"indices": [
387,
410
],
"url": "https://t.co/lQMfbuI1Ix"
}
],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2070626555710320648",
"url": "https://x.com/tonbistudio/status/2070626555710320648",
"twitterUrl": "https://twitter.com/tonbistudio/status/2070626555710320648",
"text": "Nous Research just dropped MOA (Mixture of Agents) presets inside Hermes Agent. I made a quick video showing how to set it up and create your own MOA.\n\nThe idea: mix multiple models to get capabilities beyond any single model you can use right now.\n\nHow it works:\n\nNormally Hermes sends your conversation + tools to one model.\n\nWith MOA you get several reference models plus one aggregator. The references read the conversation and offer thoughts and suggestions, but they get no tool access and never reply to you directly.\n\nThe aggregator is the one that actually acts. It sees the normal conversation plus the private advice from the references, then makes the tool calls and writes the final response.\n\nFrom Hermes's side, the aggregator's output IS the model's response, so you can use /goal or anything else like that. Cool idea, curious to see how it really performs!",
"source": "Twitter for iPhone",
"retweetCount": 143,
"replyCount": 56,
"likeCount": 1462,
"quoteCount": 5,
"viewCount": 126249,
"createdAt": "Fri Jun 26 21:53:35 +0000 2026",
"lang": "en",
"bookmarkCount": 1561,
"isReply": false,
"inReplyToId": null,
"conversationId": "2070626555710320648",
"displayTextRange": [
0,
280
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "tonbistudio",
"url": "https://x.com/tonbistudio",
"twitterUrl": "https://twitter.com/tonbistudio",
"id": "1449072997965307906",
"name": "tonbi",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2019464555844562944/y1VHgOeE_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1449072997965307906/1779265381",
"description": "",
"location": "",
"followers": 6421,
"following": 1734,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Fri Oct 15 18:01:54 +0000 2021",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 6949,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 994,
"statusesCount": 3524,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2065561010333962617"
],
"profile_bio": {
"description": "Once described as the \"Bob Ross of AI tutorials\"\nTrying to make agents and AI actually useful for everyone on Tonbi's AI Garage",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "youtube.com/@TonbisAIGarage",
"expanded_url": "http://youtube.com/@TonbisAIGarage",
"indices": [
0,
23
],
"url": "https://t.co/cjQgGYSkBG"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": false
},
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/3mspUC7jpE",
"expanded_url": "https://twitter.com/tonbistudio/status/2070626555710320648/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2070625669407715329",
"indices": [
281,
304
],
"media_key": "13_2070625669407715329",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARy8VxNf2jABAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHLxXE1/aMAEAAA==",
"media_key": "13_2070625669407715329"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2070625669407715329/img/hIqjo6JBZ0Brpq0b.jpg",
"original_info": {
"focus_rects": [],
"height": 1080,
"width": 1920
},
"sizes": {
"large": {
"h": 1080,
"w": 1920
}
},
"type": "video",
"url": "https://t.co/3mspUC7jpE",
"video_info": {
"aspect_ratio": [
16,
9
],
"duration_millis": 280533,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/amplify_video/2070625669407715329/pl/Dld6D_tMN6boF4jt.m3u8?tag=28&v=861"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2070625669407715329/vid/avc1/480x270/Jm7b2uHWqwp3pwKn.mp4?tag=28"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2070625669407715329/vid/avc1/640x360/TpvfO6qIZn50oFwd.mp4?tag=28"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2070625669407715329/vid/avc1/1280x720/I6tWynMYot01nnso.mp4?tag=28"
},
{
"bitrate": 10368000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2070625669407715329/vid/avc1/1920x1080/T0nMAkrbMQsyOORH.mp4?tag=28"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2070610321278988385",
"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
}