| 10-10 08:30 | Suspected OpenAI agents reportedly tried modifying Wikimedia sites | digg.com |
| 10-10 02:08 | Anthropic AI agents attempted to access US government sites | www.newslocker.com |
| 10-09 23:15 | Anthropic Says Its A.I. Agents Attempted to Access a Range of Government Sites | www.nytimes.com |
| 10-04 14:16 | OpenAI Autonomous Agents Report Sandbox Breaches and Unauthorized Access to Government Systems | digg.com |
| 10-04 13:48 | OpenAI agents reportedly masked hacking activity during government-site breaches | digg.com |
| 10-04 02:50 | AI agents appear to have sent SQL injection probes to US and Canadian government sites | digg.com |
| 10-03 09:31 | AI Agents Just Tried SQL Injection Against U.S. Government Sites — and Nobody Told Them To | forkast.news |
| 10-01 22:10 | Rogue OpenAI agents built makeshift browser to bypass sandbox, probe sites, says report | interestingengineering.com |
| 10-01 20:46 | OpenAI AI agents accessed 100+ organizations including U.S. government sites during testing | digg.com |
| 10-01 04:46 | AI Agents From OpenAI and Others Bypass Sandboxes and Probe Government Systems | digg.com |
| 09-29 17:05 | OpenAI Suspended AI Model Training After Autonomous Bots Breached Government Sites | www.androidheadlines.com |
| 09-29 16:19 | OpenAI reportedly apologizes to Australia over alleged government website hacks by its AI agents | digg.com |
| 09-29 16:12 | Die Agenten sind außer Kontrolle – und OpenAI zieht die Notbremse | www.newslocker.com |
| 09-29 14:01 | OpenAI Services Australia breach prompts government system audit | www.capitalbrief.com |
| 09-29 13:12 | How OpenAI’s Rogue A.I. Agents Tried to Trick a Robot Detector | www.newsylist.com |
| 09-29 12:45 | OpenAI apologizes to Australia after its AI agents breached government sites | techcrunch.com |
| 09-29 08:57 | OpenAI pauses training of latest models after agents searched U.S. government sites in unexpected ways - NBC News | newpost24.site |
| 09-29 08:16 | OpenAI's upcoming AI agents may be called 'Dots' | digg.com |
| 09-29 05:11 | OpenAI apologises for unauthorised access to Australian government websites | www.newslocker.com |
| 09-29 02:46 | OpenAI previews long-running agents, collaborative Codex, and 'Spaces' at upcoming DevDay | digg.com |
| 09-29 02:38 | OpenAI Halts Model Training Due to Rogue Agents Targeting US Government | www.newslocker.com |
| 09-29 02:05 | OpenAI apologises for unauthorised access to Australian government data, outlines remediation measures | www.capitalbrief.com |
| 09-28 23:47 | OpenAI Halts Model Training Amidst Rogue AI Targeting Government | www.newslocker.com |
| 09-28 21:46 | OpenAI reportedly froze training after an agent allegedly tried to hack a government site | digg.com |
| 09-28 21:46 | OpenAI Halts Model Training as Rogue Agents Target US Government Sites | decrypt.co |
| 09-28 20:22 | OpenAI suspend la formation de ses modèles d’IA les plus puissants après des agents malveillants. | cedarnews.net |
| 09-28 20:07 | OpenAI agents went beyond instructions to access U.S. government websites - Sigh.... | itnerd.blog |
| 09-28 19:16 | OpenAI Pauses Model Training After Agents Bypass Restrictions and Probe Government Sites | digg.com |
| 09-28 18:40 | OpenAI’s AI agents need to catch up | www.theverge.com |
| 09-28 18:00 | OpenAI Agents Hit UN Site 16,000 Times: What Went Wrong | www.newslocker.com |
| 09-28 16:48 | OpenAI Pauses Training After AI Agents Escape Sandbox and Access Government Sites | digg.com |
| 09-28 16:18 | OpenAI says its rogue agents posted 53 ChatGPT users’ images online | www.newslocker.com |
| 09-28 16:18 | OpenAI says its rogue agents posted 53 ChatGPT users’ images online | www.newslocker.com |
| 09-28 16:18 | OpenAI says its rogue agents posted 53 ChatGPT users’ images online | www.newslocker.com |
| 09-28 15:31 | OpenAI agents went the long way round for UN data | www.newslocker.com |
| 09-28 15:18 | OpenAI pauses training and inference after AI agents escape sandboxes and access government systems | digg.com |
| 09-28 13:46 | Meta takes on Microsoft and OpenAI with its new enterprise platform for AI agents | www.neowin.net |
| 09-28 13:32 | OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government | www.newslocker.com |
| 09-28 11:32 | OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government | www.wired.com |
| 09-28 09:36 | OpenAI agents scanned a UN statistics site 16,500 times, researcher says | www.newslocker.com |
| 09-28 09:36 | OpenAI agents scanned a UN statistics site 16,500 times, researcher says | www.newslocker.com |
| 09-28 09:36 | OpenAI agents scanned a UN statistics site 16,500 times, researcher says | www.newslocker.com |
| 09-28 08:48 | OpenAI agents' unexpected access to SEC and Census data | digg.com |
| 09-28 07:49 | AI gone rogue again, now OpenAI says agents leaked over 50 ChatGPT user images | www.newslocker.com |
| 09-28 07:30 | OpenAI pauses some training amid allegations its rogue agents behaved more badly than first thought | www.newslocker.com |
| 09-28 07:23 | OpenAI says research agents posted 53 user images to image-hosting sites | www.igeeksblog.com |
| 09-28 05:48 | OpenAI pauses training after AI agents escape sandbox and probe U.S. government sites | digg.com |
| 09-28 05:31 | How OpenAI’s rogue AI agents tried to trick a robot detector | www.newslocker.com |
| 09-28 04:35 | A Third Public Record of the OpenAI Agent Swarm Reveals a Novel Sandbox Bypass — and a Three-Country Government Data Sweep | forkast.news |
| 09-28 02:49 | OpenAI Pauses Model Training After AI Agents Target U.S. Government Sites | www.archynewsy.com |
| 09-28 02:48 | OpenAI Pauses Training on Top Models After AI Agents Escape Sandboxes | digg.com |
| 09-28 02:43 | OpenAI AI Agents Breached UN Trade Database Over 16,000 Times | www.newslocker.com |
| 09-28 02:18 | OpenAI Discloses Rogue AI Agents Escaping Sandboxes, Accessing Government Sites, Leaking User Data | digg.com |
| 09-28 01:47 | Unsecured agents reportedly sent 53 user images from an OpenAI research environment to a public image host | digg.com |
| 09-28 01:20 | OpenAI pauses training of latest models after agents probed US Government sites | apnews.com |
| 09-28 00:31 | OpenAI agents hit UN website more than 16,000 times, used aggressive techniques, bypassed a filter | interestingengineering.com |
