Effective Altruism Forum
Topics
EA Forum

AI benchmarks

•

Applied to Is AI Hitting a Wall or Moving Faster Than Ever? 1d ago

•

Applied to We are in a New Paradigm of AI Progress - OpenAI's o3 model makes huge gains on the toughest AI benchmarks in the world 20d ago

•

Applied to o3 22d ago

•

Applied to Trendlines in AIxBio evals 2mo ago

•

Applied to Launching the AI Forecasting Benchmark Series Q3 | $30k in Prizes 6mo ago

•

Applied to Announcing the AI Forecasting Benchmark Series | July 8, $120k in Prizes 7mo ago

•

Applied to AI Benchmarks Series — Metaculus Questions on Evaluations of AI Models Against Technical Benchmarks 10mo ago

•

Applied to A compute-based framework for thinking about the future of AI 10mo ago

•

Applied to XPT forecasts on (some) Direct Approach model inputs 10mo ago

•

Applied to Announcing Epoch's newly expanded Parameters, Compute and Data Trends in Machine Learning database 10mo ago

•

Applied to AI Forecasting Research Ideas 10mo ago

•

Applied to Announcing Epoch’s dashboard of key trends and figures in Machine Learning 10mo ago

•

Applied to Results from an Adversarial Collaboration on AI Risk (FRI) 10mo ago

•

Applied to Long list of AI questions 10mo ago

•

Applied to Language models surprised us 10mo ago

•

Applied to $250K in Prizes: SafeBench Competition Announcement 10mo ago

Toby Tremlett🔹 v1.4.0Feb 2nd 2024 GMT (+141) 1

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 1y ago

•

Applied to Encultured AI, Part 1: Enabling New Benchmarks 1y ago

•

Applied to Race to the Top: Benchmarks for AI Safety 1y ago