Safety
SafeGene: Reusable Adapters for Transferable Safety Alignment
Researchers have developed SafeGene, a method to maintain AI safety across different applications without requiring model-specific safety training. The approach addresses a critical problem where fine-tuning AI models for specific tasks can weaken their safety guardrails.
Read full story at cs.AI updates on arXiv.org →V: · A: · D:
Related
Safety
Daybreak: Tools for securing every organization in the world
OpenAI has launched Daybreak, a security-focused initiative featuring Codex Security and GPT-5.5-Cyber, framed as AI too...
Safety
AI models that can take down governments and business months away, rare Five Eyes statement warns
Intelligence agencies from Australia, the US, the UK, New Zealand, and Canada have issued an unusually public joint warn...
Safety
Tesla Driver Using Autopilot Crashes Into Home in Texas and Kills a Woman, Officials Say
A Tesla driver relying on Autopilot lost control of the vehicle, which left the roadway and struck a house in Harris Cou...