The more sophisticated AI models get, the more likely they are to lie
Human feedback training may incentivize providing any answer—even wrong ones. Jacek Krywko – Oct 4, 2024 12:39 PM SOURCE: https://arstechnica.com/science/2024/10/the-more-sophisticated-ai-models-get-the-more-likely-they-are-to-lie/ When a research team led by Amrit…