Prompts are unsafe, and that means language models are not fit for purpose by Baldur Bjarnason
Prompts are wholly insecure. They are holding back every attempt at turning language models into safe and reliable tools. Language models are not fit for purpose and should not be integrated into public-facing products unless the industry finds a new way to control them.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.