Technology ❯ Artificial Intelligence ❯ Ethics

Safety

User Interaction Regulation AI Testing Regulations Societal Impact Security Open Letter Research Concerns Global Collaboration User Protection Control Mechanisms User Security Governance Public Protests Risk Management Data Integrity Model Evaluation Superintelligence AI Alignment Discrimination Misuse Prevention Regulatory Framework

Anthropic-Led Study Finds About 250 Poisoned Documents Can Backdoor LLMs Regardless of Size

Routine safety training can largely neutralize such simple backdoors.

Yoshua Bengio Warns Preservation‑Driven AI Could Imperil Humanity Within a Decade

Leading AI Researchers Urge Chains-of-Thought Monitoring to Preserve Transparency