Topic
LLM Safety
1 story tagged LLM Safety, newest first.
Sep 17, 2026, 6:33 PMAI Security
Study Finds Google SynthID-Text Watermark Can Weaken LLM Safety
Research finds Google's SynthID-Text watermark can alter harmful-request refusals and AI agent tool calls, creating new safety risks for AI developers.
DateSectionHeadlineSource