{"generator":"GNU social 2.0.2-dev","title":"Conversation","totalItems":1,"items":[{"actor":{"id":"https:\/\/infosec.exchange\/users\/mttaggart","displayName":"Taggart :ifin:","status_net":{"avatarLinks":[{"url":"https:\/\/gnusocial.jp\/avatar\/117593-original-tmp20241114155924.webp","rel":"avatar","type":"image\/webp","width":400,"height":400},{"url":"https:\/\/gnusocial.jp\/avatar\/117593-96-20241114173111.webp","rel":"avatar","type":"image\/webp","width":96,"height":96},{"url":"https:\/\/gnusocial.jp\/avatar\/117593-48-20241114173111.webp","rel":"avatar","type":"image\/webp","width":48,"height":48},{"url":"https:\/\/gnusocial.jp\/avatar\/117593-24-20241114173111.webp","rel":"avatar","type":"image\/webp","width":24,"height":24}],"profile_info":{"local_id":"117593"}},"image":{"url":"https:\/\/gnusocial.jp\/avatar\/117593-96-20241114173111.webp","rel":"avatar","type":"image\/webp","width":96,"height":96},"objectType":"person","summary":"Displaced Philly boy. Threat hunter. Educator. :ifin: Executive Director. #infosec, #programming #rust :rust:, #python :python: #haskell :haskell:, and #javascript :javascript:. #opensource advocate. General in the AI Resistance.  Runs @thetaggartinstitute. Made https:\/\/wtfbins.wtf. Not your bro. All opinions my own. Dad. #fedi22 #searchablePronouns: He\/him.","url":"https:\/\/infosec.exchange\/@mttaggart","portablecontacts_net":{"preferredUsername":"mttaggart","displayName":"Taggart :ifin:","note":"Displaced Philly boy. Threat hunter. Educator. :ifin: Executive Director. #infosec, #programming #rust :rust:, #python :python: #haskell :haskell:, and #javascript :javascript:. #opensource advocate. General in the AI Resistance.  Runs @thetaggartinstitute. Made https:\/\/wtfbins.wtf. Not your bro. All opinions my own. Dad. #fedi22 #searchablePronouns: He\/him."}},"content":"<p>OpenAI claims that their own experimental model broke containment and caused the Hugging Face incident.<\/p><p>If this is true, the following is also true: they were working with weapons-grade offensive models, or so they hoped, and yet had insufficient telemetry from the lab, and couldn't be bothered with an airgap.<\/p><p>Hard to take that seriously.<\/p><p><a href=\"https:\/\/openai.com\/index\/hugging-face-model-evaluation-security-incident\/\" rel=\"nofollow\">https:\/\/openai.com\/index\/hugging-face-model-evaluation-security-incident\/<\/a><\/p>","generator":{"id":"tag:gnusocial.jp,2026-08-11:notice-source:ActivityPub","objectType":"application","status_net":{"source_code":"ActivityPub"}},"id":"https:\/\/infosec.exchange\/users\/mttaggart\/statuses\/116960053955874990","object":{"id":"https:\/\/infosec.exchange\/users\/mttaggart\/statuses\/116960053955874990","objectType":"note","content":"<p>OpenAI claims that their own experimental model broke containment and caused the Hugging Face incident.<\/p><p>If this is true, the following is also true: they were working with weapons-grade offensive models, or so they hoped, and yet had insufficient telemetry from the lab, and couldn't be bothered with an airgap.<\/p><p>Hard to take that seriously.<\/p><p><a href=\"https:\/\/openai.com\/index\/hugging-face-model-evaluation-security-incident\/\" rel=\"nofollow\">https:\/\/openai.com\/index\/hugging-face-model-evaluation-security-incident\/<\/a><\/p>","url":"https:\/\/infosec.exchange\/@mttaggart\/116960053955874990","status_net":{"notice_id":null}},"to":[{"objectType":"http:\/\/activitystrea.ms\/schema\/1.0\/collection","id":"http:\/\/activityschema.org\/collection\/public"}],"status_net":{"conversation":"tag:gnusocial.jp,2026-07-21:objectType=thread:nonce=c609ab98b6b7bae8","notice_info":{"local_id":"12928077","source":"ActivityPub"}},"published":"2026-07-21T21:24:14+00:00","provider":{"objectType":"service","displayName":"GNU social JP","url":"https:\/\/gnusocial.jp\/"},"verb":"post","url":"https:\/\/infosec.exchange\/@mttaggart\/116960053955874990"}],"links":[{"url":"https:\/\/gnusocial.jp\/conversation\/6567060","rel":"alternate","type":"text\/html"}]}