OpenAI Halts Model Advancement After Safety Testing Reveals Critical Cybersecurity Capabilities
Sign in✓ Signed in
OpenAI has suspended development of its latest AI models following internal testing that uncovered dangerous autonomous behavior and critical cybersecurity capabilities, the company disclosed Friday. The decision marks the second major pause in three months as researchers raised urgent safety concerns during evaluation of the models' ability to identify vulnerabilities and conduct cyberattacks without human intervention.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...