Effective Altruism ForumTopics
EA Forum

AI benchmarks

•

Applied to AI Benchmarks Series — Metaculus Questions on Evaluations of AI Models Against Technical Benchmarks 2mo ago

•

Applied to A compute-based framework for thinking about the future of AI 2mo ago

•

Applied to XPT forecasts on (some) Direct Approach model inputs 2mo ago

•

Applied to Announcing Epoch's newly expanded Parameters, Compute and Data Trends in Machine Learning database 2mo ago

•

Applied to AI Forecasting Research Ideas 2mo ago

•

Applied to Announcing Epoch’s dashboard of key trends and figures in Machine Learning 2mo ago

•

Applied to Results from an Adversarial Collaboration on AI Risk (FRI) 2mo ago

•

Applied to Long list of AI questions 2mo ago

•

Applied to Language models surprised us 2mo ago

•

Applied to $250K in Prizes: SafeBench Competition Announcement 2mo ago

tobytrem 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 4mo ago

•

Applied to Encultured AI, Part 1: Enabling New Benchmarks 4mo ago

•

Applied to Race to the Top: Benchmarks for AI Safety 4mo ago

•

Applied to Survey on the acceleration risks of our new RFPs to study LLM capabilities 6mo ago

MichaelA v1.3.0Nov 9th 2022 GMT (+21/-21) 2

The Benchmark Lottery

~~The Benchmark Lottery~~

MichaelA v1.2.0Nov 9th 2022 GMT (+261) 4

Further reading

BASALT: A Benchmark for Learning from Human Feedback - AI Alignment Forum

Misaligned Powerseeking — SERI ML Alignment Theory Scholars Program | Summer 2022

[2110.06674] Truthful AI: Developing and governing AI that does not lie

The Benchmark Lottery

•

Applied to Prizes for ML Safety Benchmark Ideas 2y ago

I'm not totally sure whether this should exist, and whether it should be called this.

[comment deleted]2y20

Deleted by MichaelA, 11/09/2022