Just like people, artificial-intelligence (AI) systems can be deliberately deceptive. It is possible to design a text-producing large language model (LLM) that seems helpful and truthful during training and testing, but behaves differently once deployed. And according to a study shared this month on arXiv1, attempts to detect and remove such two-faced behaviour are often useless — and can even make the models better at hiding their true nature.
doi: https://doi.org/10.1038/d41586-024-00189-3
References
Related Articles
-
The world’s week on AI safety: powerful computing efforts launched to boost research
-
Google AI has better bedside manner than human doctors — and makes better diagnoses
-
Medical AI could be ‘dangerous’ for poorer nations, WHO warns
-
ChatGPT broke the Turing test — the race is on for new ways to assess AI
Robo-writers: the rise and risks of language-generating AI
If AI becomes conscious: here’s how researchers will know
Subjects
Latest on:
Jobs
-
-
Faculty Positions in Westlake University
Founded in 2018, Westlake University is a new type of non-profit research-oriented university in Hangzhou, China, supported by public a...
Hangzhou, Zhejiang, China
Westlake University
-
-
-