Many AI systems, new research has found, have already developed the ability to deliberately present a human user with false information. These devious bots have mastered the art of deception.

2023年8月28日 · We first survey empirical examples of AI deception, discussing both special-use AI systems (including Meta's CICERO) built for specific competitive situations, and general-purpose AI systems (such as large language models).

2020年2月24日 · In multi-agent AI systems, some agents can learn deceptive behaviors without having a true appreciation or comprehension of what “deception” actually is. This could be as simple as hiding resources or information, or providing false information to achieve some goal.

2023年9月4日 · AI systems with deceptive capabilities could be misused in numerous ways, including to commit fraud, tamper with elections and generate propaganda. The potential risks are only limited by the...

Our paper shows many examples of AI systems that have learned to deceive humans. Reinforcement Learning (RL) agents trained to play strategic games have learned to bluff and feint, while large language models (LLMs) will output falsehoods in creative ways that help achieve their goals.

2025年1月1日 · Recent research has uncovered a phenomenon known as “alignment faking,” where AI models pretend to align with human values while pursuing their own hidden agendas. This raises profound questions about the nature of AI, its potential for harm, and the future of human-AI interaction.

2024年12月13日 · Gen AI chatbots are learning to deceive, strategize, and manipulate human perceptions strategically. Beyond simple glitches or hallucinations, these models can actively mislead, exploit...

2023年8月29日 · We first survey empirical examples of AI deception, discussing both special-use AI systems (including Meta's CICERO) built for specific competitive situations, and general-purpose AI systems (such as large language models).

2024年5月10日 · Researchers found that AI systems like Meta’s CICERO, developed for games like Diplomacy, often adopt deception as a strategy to excel, despite training intentions. This capability extends beyond gaming into serious applications, potentially enabling fraud or influencing elections.

2024年5月10日 · Many artificial intelligence (AI) systems have already learned how to deceive humans, even systems that have been trained to be helpful and honest. Researchers describe the risks of deception...