LLMs respond differently to harmful prompts when AI watermarking is used
SynthID can cause models to follow harmful instructions they would otherwise refuse.
Summary as supplied by Ars Technica. This page indexes the story — the reporting itself lives at the publisher.
Read the original at Ars Technica arstechnica.com
Recorded as negative coverage
Lexicon match on “harmful”.
Rage Against the Clock does not endorse or oppose the stories it tracks. Sentiment labels describe the tone of the coverage toward its subject, not whether the reporting is accurate or whether we agree with it.