Ars TechnicaOct 4, 2024

The more sophisticated AI models get, the more likely they are to lie

Human feedback training may incentivize providing any answer—even wrong ones.

https://arstechnica.com/science/2024/10/the-more-sophisticated-ai-models-get-the-more-likely-they-are-to-lie/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social

The more sophisticated AI models get, the more likely they are to lie

Human feedback to AIs makes them favor providing an answer, even a wrong one, while making the answer more convincing.

Ars Technica
Show threadBurstaholic
@arstechnica that is how models work - you'll ALWAYS get another token, whether it not it makes sense
Oct 4, 2024 at 9:28pmWeb