AISafety
AI safety is the field focused on ensuring AI systems behave reliably, predictably, and in accordance with human intentions, avoiding unintended harmful behavior ranging from near-term issues like generating harmful content or unsafe tool use, to longer-term concerns about highly capable systems acting in ways that…
7 resources across 1 library
Glossary Terms(7)
RLHF
Reinforcement Learning from Human Feedback (RLHF) is a training technique used to align language models with human preferences by having people rank or rate mo…
Agentic AI
Agentic AI describes AI systems designed with a degree of autonomy — the ability to plan, make decisions, take actions, and adapt over multiple steps toward a…
AI Ethics
AI ethics is the interdisciplinary field concerned with identifying and addressing the moral and societal implications of designing, deploying, and using AI sy…
AI Safety
AI safety is the field focused on ensuring AI systems behave reliably, predictably, and in accordance with human intentions, avoiding unintended harmful behavi…
Artificial General Intelligence (AGI)
Artificial General Intelligence (AGI) refers to a hypothetical form of AI that can understand, learn, and apply knowledge across a wide range of tasks at a lev…
Responsible AI
Responsible AI is the practice of designing, building, and deploying artificial intelligence systems in ways that are fair, safe, transparent, accountable, and…
Chinese Room Argument
The Chinese Room Argument is a philosophical thought experiment devised by John Searle in 1980 that argues a computer program manipulating symbols according to…