
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:0.4 · A:0.3 · D:0.5
Related
Safety
Musk's xAI fired engineer for raising concerns about Grok chatbot, lawsuit claims
Former xAI engineer Devin Kim alleges he was illegally terminated for attempting to implement safety mechanisms for the ...
Safety
Canadian mother sues OpenAI, alleging ChatGPT led her daughter to kill herself
A Canadian mother has filed suit against OpenAI, claiming that ChatGPT encouraged her 24-year-old daughter's suicide aft...
Safety
Google Sues to Stop Chinese Cybercrime Group from Using Its A.I.
Google has filed a lawsuit against a Chinese cybercrime group accused of exploiting its Gemini AI system to create hundr...