Should we be worried about malicious use of AI language models? – ComputerWeekly.com
Patrick Daxenbichler – FotoliaMore and more evidence is emerging into how large language models, such as Generative Pre-trained Transformer 3 (GPT-3) used by the likes of OpenAI’s advanced ChatGPT chatbot, seem to be highly vulnerable to abuse through creative prompt engineering by malicious actors.Moreover, as the capabilities of such models hit the mainstream, new approaches … Read more