🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

// Self-Harness: Harnesses That Improve Themselves // (bookmark this one) Most of the agent scaffolds we rely on today are built once and remain frozen or mostly unchanged. The harness, like the skills, needs to evolve with new models. What if the scaffold rewrites itself? This new work treats the harness, the prompts, tools, and control flow around the model as a learnable artifact that improves from its own runs rather than staying a fixed wrapper you hand-maintain. The scaffolding becomes the part that compounds, run after run. If you run long-horizon agents, a self-modifying harness turns scaffold upkeep from manual work into something the system earns on its own. Paper: https://t.co/byh1MP99xU Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2064429834999304247/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2064429834999304247/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-06-11T22:56:23.247481",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2064429834999304247",
  "url": "https://x.com/omarsar0/status/2064429834999304247",
  "twitterUrl": "https://twitter.com/omarsar0/status/2064429834999304247",
  "text": "// Self-Harness: Harnesses That Improve Themselves //\n\n(bookmark this one)\n\nMost of the agent scaffolds we rely on today are built once and remain frozen or mostly unchanged.\n\nThe harness, like the skills, needs to evolve with new models.\n\nWhat if the scaffold rewrites itself?\n\nThis new work treats the harness, the prompts, tools, and control flow around the model as a learnable artifact that improves from its own runs rather than staying a fixed wrapper you hand-maintain.\n\nThe scaffolding becomes the part that compounds, run after run. If you run long-horizon agents, a self-modifying harness turns scaffold upkeep from manual work into something the system earns on its own.\n\nPaper: https://t.co/byh1MP99xU\n\nLearn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX",
  "source": "Twitter for iPhone",
  "retweetCount": 100,
  "replyCount": 26,
  "likeCount": 524,
  "quoteCount": 4,
  "viewCount": 30679,
  "createdAt": "Tue Jun 09 19:30:02 +0000 2026",
  "lang": "en",
  "bookmarkCount": 691,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2064429834999304247",
  "displayTextRange": [
    0,
    277
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 306907,
    "following": 857,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 36496,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4701,
    "statusesCount": 18157,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2064741062761992597"
    ],
    "profile_bio": {
      "description": "Building self-improving AI @dair_ai • Prev: Meta AI | PhD • Learn about AI Agents for FREE here: https://t.co/P5SA9u54xO",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "academy.dair.ai/courses/elemen…",
              "expanded_url": "https://academy.dair.ai/courses/elements-of-ai-agents",
              "indices": [
                97,
                120
              ],
              "url": "https://t.co/P5SA9u54xO"
            }
          ],
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                27,
                35
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypkSM"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/QDi4JTVMA1",
        "expanded_url": "https://twitter.com/omarsar0/status/2064429834999304247/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2064429831320993792",
        "indices": [
          278,
          301
        ],
        "media_key": "3_2064429831320993792",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARymU/5nm4AACgACHKZT/0LaEDcAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHKZT/mebgAAKAAIcplP/QtoQNwAA",
            "media_key": "3_2064429831320993792"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HKZT_mebgAAaFiV.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 898,
              "w": 1604,
              "x": 0,
              "y": 0
            },
            {
              "h": 1604,
              "w": 1604,
              "x": 0,
              "y": 0
            },
            {
              "h": 1829,
              "w": 1604,
              "x": 0,
              "y": 0
            },
            {
              "h": 1882,
              "w": 941,
              "x": 141,
              "y": 0
            },
            {
              "h": 1882,
              "w": 1604,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1882,
          "width": 1604
        },
        "sizes": {
          "large": {
            "h": 1882,
            "w": 1604
          }
        },
        "type": "photo",
        "url": "https://t.co/QDi4JTVMA1"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2606.09498",
        "expanded_url": "https://arxiv.org/abs/2606.09498",
        "indices": [
          691,
          714
        ],
        "url": "https://t.co/byh1MP99xU"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          767,
          790
        ],
        "url": "https://t.co/1e8RZKs4uX"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}