3 stories, newest first · one card per story
Untag attack framework renders existing token- and weight-level trigger-tag misuse detection mechanisms in open-weight LLMs entirely ineffective, researchers demonstrate.
Anthropic launches Enterprise Frontier Safeguards, letting regulated customers keep Claude usage logs in their own cloud storage under their own keys with automated misuse detection.
OpenAI previews Private Safety Processing, detecting cross-interaction AI misuse without exposing customer prompt content, rolling out in September.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views