A Georgia Tech Ph.D. student is investigating whether internal signals in large language models could help identify harmful behavior before it reaches users.

What has the consistency of both toothpaste and dough, can absorb twice its weight in water and still remain sticky, was used by medieval artists as a binder in paint and has been hypothesized by physicians to repel insects?

The award comes from the Economic Development Administration’s (EDA) Disaster supplemental funding and is supported by $24 million in private investment.

Georgia Tech researchers have developed a new neural framework that examines how different training sources influence empathy and social reasoning within large language models.

Georgia Tech researchers found that instruction changes can reduce chatbots’ reinforcement of delusional beliefs.

Maritime cybersecurity training leaves sailors vulnerable to attacks that manipulate ship systems without obvious failures. The Georgia Tech study identifies weaknesses in preparation and threat recognition among military mariners.

Researchers find that deleted local AI chats may remain recoverable from a phone’s memory through a new tool called ORISA.

The three-year initiative gives researchers greater access to AI tools, training, and computing power to help accelerate scientific breakthroughs.

AI agents don’t go rogue. That’s something only humans do.

The three-year initiative gives researchers greater access to AI tools, training, and computing power to help accelerate scientific breakthroughs.