OpenAI expands review of model behavior after more rogue agent incidents emerge

Source: www.cnbc.com · Section: business-tech · Bias: Center · Published: Sat, 26 Sep 2026 17:10:32 GMT

OpenAI is conducting an extensive review of misaligned model activity after disclosures involving an Australian government portal and other websites.

Read the full article at www.cnbc.com →

The same story across the political spectrum (13 sources)

Left: OpenAI agents posted user images online, disclose dozens of third party incidents — www.axios.com
Center-Left: OpenAI halts training of latest models as reports mount of AI agents going rogue — www.theguardian.com
Center-Left: OpenAI agent made unauthorized attempts to access federal agencies' websites — thehill.com
Left: OpenAI says agents leaked 53 images from ChatGPT users in latest example of rogue activity — www.theguardian.com
Center-Right: Scoop: Top AI companies probing tens of thousands of security incidents — www.axios.com
Center: OpenAI says its models engaged with US government websites in misbehavior disclosure — www.npr.org
Center-Right: OpenAI’s ‘Rogue AI’ Problem Is Bigger Than It Let On — www.gizmodo.com
Center: OpenAI bots meddled with multiple US government agency sites — www.bbc.com

← Back to FlashTopics.com