The Pentagon's Chief Digital and Artificial Intelligence Office (CDAO) has launched a bug bounty exercise to detect biases in AI systems, with a focus on large language models.
The exercise will run from Jan. 29 through Feb. 27 and will identify unknown areas of risk in large language models, starting with open-source chatbots.
The bug bounty exercise is being overseen by ConductorAI and Bugcrowd and offers a $24,000 pot for identifying instances of protected class bias.