AI benchmarks
•
Applied to A compute-based framework for thinking about the future of AI 1mo ago
•
Applied to XPT forecasts on (some) Direct Approach model inputs 1mo ago
•
Applied to AI Forecasting Research Ideas 1mo ago
•
Applied to Announcing Epoch’s dashboard of key trends and figures in Machine Learning 1mo ago
•
Applied to Results from an Adversarial Collaboration on AI Risk (FRI) 1mo ago
•
Applied to Long list of AI questions 1mo ago
•
Applied to Language models surprised us 1mo ago
•
Applied to $250K in Prizes: SafeBench Competition Announcement
1mo ago
Benchmarks are tests which enable us to measure the progress of AI capabilities, and test for characteristics which might pose safety risks.
•
Applied to Open Phil releases RFPs on LLM Benchmarks and Forecasting 3mo ago
•
Applied to Encultured AI, Part 1: Enabling New Benchmarks 3mo ago
•
Applied to Race to the Top: Benchmarks for AI Safety 3mo ago
•
Applied to Survey on the acceleration risks of our new RFPs to study LLM capabilities 5mo ago
•
Applied to Prizes for ML Safety Benchmark Ideas 1y ago
I'm not totally sure whether this should exist, and whether it should be called this.