The purpose of this workshop, which was supported by the Engineering for Humanitarian Action (EHA) initiative, was to help ICRC staff members understand the implications of NLP and LLMs for their work. The content covered an introduction to the technology, presentations of practical use cases, and a discussion of safety and ethical considerations. On Monday, a (hybrid) workshop on natural language processing (NLP) and large language models (LLMs) was held at the International Committee of the Red Cross - ICRC headquarters, co-organised and conducted by researchers from Ecole polytechnique fédérale de Lausanne and ETH Zurich with members of the ICRC, and coordinated by Prof. Meta's board game-playing AI can pass as a human in game negotiations Yes, other AIs have achieved human-level performance in games like Go and chess, but playing this game, Diplomacy, involves rather complex skills such as negotiation, cooperation, and competition. Meta AI researchers developed Cicero, an AI program that was able to beat most human players in the online board game of Diplomacy. To create it, researchers combined a reasoning engine with a dialogue model, allowing it to communicate and predict the moves of others. But yes "what impresses me the most is its ability to communicate with empathy and build rapport" What can possible go wrong? On why we need to prioritise AI safety NOW - the newly released AI system trained to strategise world conquest, negotiate in English with humans, blissfully unaware of the interaction with a machine, lie although programmed to tell the truth and manipulate other human players to act according with its own goals.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |