How truthful is GPT-3? A benchmark for language models – AI Alignment Forum

This is an edited excerpt of a new ML paper (pdf, code) by Stephanie Lin (FHI Oxford), Jacob Hilton (OpenAI) and Owain Evans (FHI Oxford). The paper is under review at NeurIPS. TITLE: TRUTHFULQA: MEASURING HOW MODELS MIMIC HUMAN FALSEHOODS ABSTRACT We propose a benchmark to measure whether a language model is truthful in generatingContinue reading “How truthful is GPT-3? A benchmark for language models – AI Alignment Forum”

Google Search Engine | Information Systems & Technology

IS&T recommends that website owners use the MIT Search Box (via search.mit.edu) for basic MIT-branded search, the MIT Google Custom Search Engine (CSE) if a more integrated experience is needed, or set up and administer their own Google Custom Search Engine (CSE) for embedded, branded results and highly configurable custom search. More information on each ofContinue reading “Google Search Engine | Information Systems & Technology”