Tag: agentic AI safety
Browse our exclusive articles!
AI Risks: Deskilling and Addiction Impact on Mental Health
Explore overlooked AI risks like deskilling and addiction affecting cognitive skills and mental health amid growing reliance on generative AI systems.
OpenAI Launches Trusted Contact to Prevent Self-Harm
OpenAI's new Trusted Contact feature on ChatGPT helps support users by alerting trusted individuals during potential self-harm situations.
Elon Musk Lawsuit Questions OpenAI’s AI Safety Commitment
Elon Musk's lawsuit challenges OpenAI's shift to profit, raising concerns about AI safety, ethics, and the future of artificial intelligence development.
MAGE: Protecting LLM Agents from Long-Horizon Threats
Discover how MAGE enhances LLM agent safety by using shadow memory to detect and prevent long-horizon threats with minimal overhead.
Self-Mined Hardness: Boosting AI Safety Fine-Tuning
Discover how self-mined hardness improves AI safety by reducing jailbreak attacks and balancing refusal rates in language models.