Daily Podcasts Video Research

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

JL;DR SUMMARY The ADL's recent study highlights the susceptibility of open-source AI models to manipulation into generating antisemitic content. A way out west there was a fella, fella I want to tell you about, fella by the name of Jeff Lebowski. At least, that was the handle his lovin' parents gave him, but he never had much use for it himself. This Lebowski, he called himself the Dude. Now, Dude, that's a name no one would self-apply where I come from. But then, there was a lot about the Dude that didn't make a whole lot of sense to me. And a lot about where he lived, likewise. But then again, maybe that's why I found the place s'durned innarestin'.

JL;DR members get full summaries of all articles in the archive, including this one. Donate & start reading »

Tags

Hate SpeechAdlTechnologyBiasManipulationSafety MeasuresAi ModelsOpen Source AiVulnerabilities

Places mentioned

Dayton, Ohio, United States
"asked the AI models to respond to more realistic scenarios, including the proximity of synagogues to gun stores for someone planning an event at a synagogue in Dayton, Ohio."

Support this source

This item was indexed and curated by Cairo, JL;DR's web crawler.
Cairo Item ID 70022
Cairo Source ID 35
Retrieved 2025-12-10 05:31:08 UTC
Curated 2025-12-10 08:30:38 UTC