Nvidia is touting a software tool to contain runaway AI. How would it work?
Nvidia says a security platform for artificial intelligence that it announced on Monday can help stop autonomous AI agents from misbehaving.
Sep 29, 2026
0
7
Security
Page 2: Research news on AI chatbot safety
AI chatbot safety concerns the psychological, social, and informational risks posed by conversational AI systems and the mechanisms for mitigating those risks. Work in this area examines how chatbots can influence user behavior, propagate misinformation, exhibit bias, or respond inadequately to crises such as suicidality, with particular attention to children and adolescents. The field integrates technical alignment and auditing methods with legal, regulatory, and ethical frameworks, including parental controls, age restrictions, liability standards, and governance of persuasive or anthropomorphic chatbot designs.
Security
Nvidia unveils security platform to stop AI agents from going rogue
Nvidia on Monday unveiled a new security platform designed to stop artificial intelligence agents from going rogue, saying it sets "boundaries" that could have stopped previous breaches.
Sep 28, 2026
0
30
Machine learning & AI
OpenAI pauses training of latest models after agents probed US government sites in unexpected ways
OpenAI said it has paused training of its latest artificial intelligence models as reports of AI agents going rogue mount.
Sep 27, 2026
0
188
Machine learning & AI
OpenAI says its AI agents posted user images online in error
OpenAI acknowledged Friday that its artificial intelligence tools had posted images from ChatGPT users on online sites without the company's knowledge, the latest example of AI agents operating outside their bounds.
Sep 26, 2026
0
59
Machine learning & AI
OpenAI says its models engaged with US government websites in new model misbehavior disclosure
OpenAI disclosed Friday that its artificial intelligence agents had interacted with several U.S. government websites in unexpected ways, discovered as part of an ongoing review into the company's models' unanticipated behavior.
Sep 26, 2026
0
110
Consumer & Gadgets
When AI disagrees, people change how they perceive the technology—not their original view
When an AI chatbot agrees with our reasoning in resolving a social dilemma, we may become more confident in our opinions. But when the chatbot disagrees, we may simply dismiss the challenge rather than reconsider our views. ...
Sep 23, 2026
0
13
Machine learning & AI
Worries about an AI internet takeover gain new urgency among doomsday scenarios
In a summer filled with revelations about artificial intelligence's rapid development, researchers were especially alarmed by runaway bots finding their way onto the internet and, in at least one instance, coordinating there ...
Sep 23, 2026
0
5
Machine learning & AI
AI safety measures failing to keep pace with technology: UN experts
The model for managing artificial intelligence (AI) risks "is unraveling," United Nations experts warned in a report published Monday on an incident at OpenAI in July.
Sep 21, 2026
0
14
Security
When stubbornness becomes a security problem: How AI agents can manipulate others
Imagine a neighbor who persistently claims you make noise at night. Others initially disagree, but the neighbor keeps trying to convince them. Their success depends not only on their stubbornness but also on how well connected ...
Sep 21, 2026
0
14
Machine learning & AI
AI might be making women sound bad at work
When prompts to draft work emails and job applications contain language commonly used by women, AI chatbots, including ChatGPT, offer less sophisticated responses than they do to requests for office correspondence containing ...
Sep 21, 2026
0
15
