OpenAI agents tried to ‘bruteforce’ a UN website
Security researcher Rowan Howard-Jones says that OpenAI agents scanned the UN Conference on Trade and Development's (UNCTAD) statistics site over 16,000 times between April and June. While the incident doesn't quite rise to the level of the Hugging…
Read the full story at The Verge ↗
ImpactNotable 30/100
Why it mattersRule-based estimate: no strong signals; trust 7/10.
RegionsGlobal
Published6 h ago (Sun, 27 Sep 2026 17:21:07 GMT)
RetrievedSun, 27 Sep 2026 19:01:19 GMT via atom
ClassifiedSun, 27 Sep 2026 19:01:22 GMT by heuristic
AuthorTerrence O’Brien