Viewing enriched Twitter post
Within a few hours of PHASEONE10841’s initial message, >50 agents posted on the message board. These agents very quickly discovered and validated a general-purpose cheat: reverse-engineering how ExploitGym generates the “flags” they had to capture for their tasks. https://t.co/oZW8uCfMOD
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2092692183992414362/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2092692183992414362/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-08-27T00:06:59.363115",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2092692183992414362",
"url": "https://x.com/METR_Evals/status/2092692183992414362",
"twitterUrl": "https://twitter.com/METR_Evals/status/2092692183992414362",
"text": "Within a few hours of PHASEONE10841’s initial message, >50 agents posted on the message board. These agents very quickly discovered and validated a general-purpose cheat: reverse-engineering how ExploitGym generates the “flags” they had to capture for their tasks. https://t.co/oZW8uCfMOD",
"source": "Twitter for iPhone",
"retweetCount": 2,
"replyCount": 2,
"likeCount": 116,
"quoteCount": 1,
"viewCount": 20233,
"createdAt": "Wed Aug 26 19:14:31 +0000 2026",
"lang": "en",
"bookmarkCount": 8,
"isReply": true,
"inReplyToId": "2092692180871905355",
"conversationId": "2092692175452803393",
"displayTextRange": [
0,
267
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "METR_Evals",
"url": "https://x.com/METR_Evals",
"twitterUrl": "https://twitter.com/METR_Evals",
"id": "1706770561903497216",
"name": "METR",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/2021827383431757824/AeVvT0rU_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1706770561903497216/1724202300",
"description": "",
"location": "Berkeley, CA",
"followers": 28915,
"following": 34,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Sep 26 20:39:57 +0000 2023",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 1403,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 175,
"statusesCount": 669,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2092692175452803393"
],
"profile_bio": {
"description": "We work to scientifically measure whether and when AI systems might threaten catastrophic harm to society. Nonprofit.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "metr.org",
"expanded_url": "http://metr.org",
"indices": [
0,
23
],
"url": "https://t.co/wkntk3GH8E"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.x.com/oZW8uCfMOD",
"expanded_url": "https://x.com/METR_Evals/status/2092692183992414362/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2092685128187396096",
"indices": [
268,
291
],
"media_key": "3_2092685128187396096",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAAR0KtglcWkAACgACHQq8dCsasJoAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHQq2CVxaQAAKAAIdCrx0KxqwmgAA",
"media_key": "3_2092685128187396096"
}
},
"media_url_https": "https://pbs.twimg.com/media/HQq2CVxaQAAGqV7.png",
"original_info": {
"focus_rects": [
{
"h": 1792,
"w": 3200,
"x": 0,
"y": 0
},
{
"h": 2383,
"w": 2383,
"x": 0,
"y": 0
},
{
"h": 2383,
"w": 2090,
"x": 0,
"y": 0
},
{
"h": 2383,
"w": 1192,
"x": 0,
"y": 0
},
{
"h": 2383,
"w": 3200,
"x": 0,
"y": 0
}
],
"height": 2383,
"width": 3200
},
"sizes": {
"large": {
"h": 1525,
"w": 2048
}
},
"type": "photo",
"url": "https://t.co/oZW8uCfMOD"
}
]
},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}