OpenAI expands review of model behavior after more rogue agent incidents emerge
Source:
cnbc
September 26, 2026 · 10:10
From the publisher
OpenAI is conducting an extensive review of misaligned model activity after disclosures involving an Australian government portal and other websites.
The original article opens on the publisher's website.
More from General
View topic →Australian backlash to datacentres is faux import from US, officials say: ‘We are not the United States’
guardianTech
Sep 26, 2026 · 15:00
Trump gave Xi Jinping a warm welcome. What did the talks accomplish?
nprNews
Sep 26, 2026 · 14:13
Insurers claim AI is already increasing healthcare costs
techcrunch
Sep 26, 2026 · 14:02
Boeing flags 737 Max software glitch affecting some automated approach functions
cnbc
Sep 26, 2026 · 13:30
TikTok agrees to pay at least $100M in Alabama settlement
techcrunch
Sep 26, 2026 · 13:24
Countries mentioned