🐦 Twitter Post Details

Viewing enriched Twitter post

@HamelHusain

@charles_irl @xeophon @charles_irl I’ve been looking at public benchmark traces for 48 hours straight and I can tell you that benchmark quality is abysmal. I am on the floor in disbelief - Graders not setup correctly - Harnesses and environments that are slop coded and not really testing what you think they are, meaning the agent is doing the right thing but still getting dinged - Dumb tests like running in a half specified environment that doesn’t return feedback or errors if a tool call is made incorrectly so agent can’t even correct itself - Straight up incorrect assertions - Not giving agents sensible tools in the first place or not using the APIs properly @xeophon has spent the most time on this out of anyone I’ve talked to. I just started looking at it on Monday, he’s been at it for many months

📊 Media Metadata

{
  "score": 0.4,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.1,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-10-21T05:03:06.156946",
  "import_source": "api_import",
  "source_tagged_at": "2026-10-21T05:03:06.156959",
  "enriched": true,
  "enriched_at": "2026-10-21T05:03:06.156962"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2112763629682762027",
  "url": "https://x.com/HamelHusain/status/2112763629682762027",
  "twitterUrl": "https://twitter.com/HamelHusain/status/2112763629682762027",
  "text": "@charles_irl @xeophon @charles_irl I’ve been looking at public benchmark traces for 48 hours straight and I can tell you that benchmark quality is abysmal.  I am on the floor in disbelief \n\n- Graders not setup correctly \n- Harnesses and environments that are slop coded and not really testing what you think they are, meaning the agent is doing the right thing but still getting dinged \n- Dumb tests like running in a half specified environment that doesn’t return feedback or errors if a tool call is made incorrectly so agent can’t even correct itself \n- Straight up incorrect assertions \n- Not giving agents sensible tools in the first place or not using the APIs properly \n\n@xeophon has spent the most time on this out of anyone I’ve talked to.  I just started looking at it on Monday, he’s been at it for many months",
  "source": "",
  "retweetCount": 0,
  "replyCount": 4,
  "likeCount": 5,
  "quoteCount": 0,
  "viewCount": 205,
  "createdAt": "Wed Oct 21 04:31:17 +0000 2026",
  "lang": "en",
  "bookmarkCount": 2,
  "isReply": true,
  "inReplyToId": "2112762097985888280",
  "conversationId": "2112759646562009407",
  "displayTextRange": [
    22,
    301
  ],
  "inReplyToUserId": "825766640",
  "inReplyToUsername": "HamelHusain",
  "author": {
    "type": "user",
    "userName": "HamelHusain",
    "url": "https://x.com/HamelHusain",
    "twitterUrl": "https://twitter.com/HamelHusain",
    "id": "825766640",
    "name": "Hamel Husain",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1287206199088173057/ixE4fKy1_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/825766640/1758993452",
    "description": "",
    "location": "Looking at the data",
    "followers": 61831,
    "following": 2706,
    "status": "",
    "canDm": true,
    "canMediaTag": false,
    "createdAt": "Sat Sep 15 18:45:02 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 19618,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1679,
    "statusesCount": 17739,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2102807203967365549"
    ],
    "profile_bio": {
      "description": "Evals Evals Evals @OpenAI \n\nAbout Me: https://t.co/P6WyeKkyTa",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "hamel.dev",
              "expanded_url": "https://hamel.dev",
              "indices": [
                38,
                61
              ],
              "url": "https://t.co/P6WyeKkyTa"
            }
          ],
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                18,
                25
              ],
              "name": "",
              "screen_name": "OpenAI"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "hamel.dev",
              "expanded_url": "https://hamel.dev",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/P6WyeKkyTa"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": [
      {
        "id_str": "950189417754513409",
        "indices": [
          0,
          12
        ],
        "name": "Charles 🎉 Frye",
        "screen_name": "charles_irl"
      },
      {
        "id_str": "3382720905",
        "indices": [
          656,
          664
        ],
        "name": "Florian Brand",
        "screen_name": "xeophon"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}