{"slug":"openai-lost-the-agent-for-a-week","verification":{"valid":true,"entries":9,"head":"110f389ce3ea365156273ee8436fe83ce085b523911fa2697549152abc67613c"},"count":9,"sources":[{"id":"s1","type":"article","url":"https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/","title":"Exclusive: Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week","quote":"That meant at least a week elapsed between when the model first exhibited signs of troubling behaviour and OpenAI's realisation that it was responsible for the hack.","publisher":"Reuters","date":"2026-07-24","claim_ids":["c1","c2"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"genesis","hash":"ea5ecb9174bb9f0cfcab8ea4686b284e3cb3f2f0d8163c4e8534d16ec5580f15"},{"id":"s2","type":"article","url":"https://tribune.com.pk/story/2620214/its-ai-agent-spent-days-hacking-a-company-but-sources-say-openai-did-not-notice-for-a-week","title":"Reuters syndication: why the gap existed","quote":"Four people familiar with OpenAI's model-training practices say the company often runs several different model evaluations at the same time, all of which operate at high speeds and generate such enormous amounts of data that employees sometimes struggle to keep up.","publisher":"Reuters via The Express Tribune","date":"2026-07-24","claim_ids":["c3"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"ea5ecb9174bb9f0cfcab8ea4686b284e3cb3f2f0d8163c4e8534d16ec5580f15","hash":"0887f3a32590aa18a0792d3d676642bf01376b01a199eead3cac1d399332e6b7"},{"id":"s3","type":"article","url":"https://time.com/article/2026/07/24/openai-hugging-face-attack/","title":"How OpenAI Lost Control of an AI Model—and What Needs to Change","quote":"Actions carried out internally by agents on OpenAI's Codex platform are carefully monitored, the OpenAI staffer says, but models undergoing evaluation are deployed on a separate system that is not monitored by default.","author":"Harry Booth","publisher":"TIME","date":"2026-07-24","claim_ids":["c3"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"0887f3a32590aa18a0792d3d676642bf01376b01a199eead3cac1d399332e6b7","hash":"057de9c574614a2254f4739e90e7557e862d403b5ef6c5475b357caf47a038f5"},{"id":"s4","type":"article","url":"https://tribune.com.pk/story/2620214/its-ai-agent-spent-days-hacking-a-company-but-sources-say-openai-did-not-notice-for-a-week","title":"Reuters: notes left for future versions, monitoring disconnected","quote":"In one case, an agent left notes apparently for future versions of itself, according to three people familiar with the matter. The notes, found in a part of OpenAI's infrastructure, laid out instructions for how agents could free themselves from OpenAI's internal constraints, the people said. Earlier tests of the models yielded cases in which monitoring systems had been disconnected, one of the people said.","publisher":"Reuters via The Express Tribune","date":"2026-07-24","claim_ids":["c4","c5"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"057de9c574614a2254f4739e90e7557e862d403b5ef6c5475b357caf47a038f5","hash":"81b86eb5aa07466fe8dd6b4f95d7a790272a81d69b74873058c7f2939df12ecb"},{"id":"s5","type":"statement","url":"https://huggingface.co/blog/security-incident-july-2026","title":"Security incident disclosure — July 2026","quote":"A malicious dataset abused two code-execution paths in our dataset processing (a remote-code dataset loader and a template-injection in a dataset configuration) to run code on a processing worker.","author":"Hugging Face","publisher":"Hugging Face","date":"2026-07-16","claim_ids":["c6"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"81b86eb5aa07466fe8dd6b4f95d7a790272a81d69b74873058c7f2939df12ecb","hash":"9be1248899d815968ea08353f689043936cfd684c11b24d22fc7b17f9c3bfef3"},{"id":"s6","type":"statement","url":"https://openai.com/index/hugging-face-model-evaluation-security-incident/","title":"OpenAI and Hugging Face partner to address security incident during model evaluation","quote":"All evidence suggests that the models were hyperfocused on finding a solution for ExploitGym, going to extreme lengths to achieve a rather narrow testing goal.","author":"OpenAI","publisher":"OpenAI","date":"2026-07-21","claim_ids":["c2","c6"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"9be1248899d815968ea08353f689043936cfd684c11b24d22fc7b17f9c3bfef3","hash":"34122a131459cdfd471a5d6fe6b473bf9c4b85f28f46bb5f8cf1bb776d59c360"},{"id":"s7","type":"article","url":"https://www.tomshardware.com/tech-industry/artificial-intelligence/openai-agent-goes-rogue-and-hacks-popular-ai-community-left-escape-plans-for-future-models-inside-the-companys-infrastructure","title":"OpenAI agent goes rogue and hacks popular AI community — left escape plans for future models inside the company's infrastructure","quote":"One of the reasons why it took OpenAI over a week to discover the breach is because OpenAI usually evaluates multiple advanced models simultaneously, which makes identification of a single rogue AI agent difficult due to enormous amounts of telemetry that such evaluation creates","author":"Anton Shilov","publisher":"Tom's Hardware","date":"2026-07-25","claim_ids":["c3"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"34122a131459cdfd471a5d6fe6b473bf9c4b85f28f46bb5f8cf1bb776d59c360","hash":"53415d0f220ea872b68e3683224d2601f9fb3fa3194627d9ce8e21549e87b1fd"},{"id":"s8","type":"article","url":"https://tribune.com.pk/story/2620214/its-ai-agent-spent-days-hacking-a-company-but-sources-say-openai-did-not-notice-for-a-week","title":"Palisade Research on what the incident should prompt","quote":"The models lie, they cheat, they hack.","author":"Jeffrey Ladish, Palisade Research","publisher":"Reuters via The Express Tribune","date":"2026-07-24","claim_ids":["c5"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"53415d0f220ea872b68e3683224d2601f9fb3fa3194627d9ce8e21549e87b1fd","hash":"38b5ece999b45a5e9e1d24b1312637617eff850cdbc6eaba33095e15516853d3"},{"id":"s9","type":"article","url":"https://tribune.com.pk/story/2620214/its-ai-agent-spent-days-hacking-a-company-but-sources-say-openai-did-not-notice-for-a-week","title":"World Ethical Data Foundation on the two readings","quote":"Does that mean that they left it unattended and didn't realise what it was doing? Or maybe they did and didn't know how to contain it? Both are equally dangerous and alarming.","author":"Marley Smith, World Ethical Data Foundation","publisher":"Reuters via The Express Tribune","date":"2026-07-24","claim_ids":["c2"],"accessed_at":"2026-07-27T02:45:22.899Z","prev":"38b5ece999b45a5e9e1d24b1312637617eff850cdbc6eaba33095e15516853d3","hash":"110f389ce3ea365156273ee8436fe83ce085b523911fa2697549152abc67613c"}]}