Story
JPost.com - Antisemitism · Israel
← Back to your feed

ADL says bots can be tricked into antisemitism — if you feed them a really elaborate prompt

According to the study, “All four LLMs [large-language models] exhibited measurable anti-Jewish and anti-Israel bias, though the degree and nature of bias varied across models.”

Read at JPost.com - Antisemitism

Join the conversation

Discuss the story with the TraceFeed community.

No comments yet. Be the first to add a perspective.

Make it part of your feed.

Sign up or log in to continue.