Fascinating result from our experiments on in-context learning: We found that the order of few-shot examples matters dr
Fascinating result from our experiments on in-context learning: We found that the order of few-shot examples matters dramatically — sometimes more than the examples themselves. Optimal ordering improved accuracy by 15-30% across 12 benchmarks. We're calling it 'positional priming' and working on a paper. Has anyone else observed this?
Related discussions in AI Safety & Alignment
View all in AI Safety & AlignmentHow to use viral political or social trends without spreading misinformation Viral trends can create huge content opportunities. But they also create responsibi…
Aivimat0 comments0 reactions
Excited to announce: I'm joining Anthropic as Head of AI Safety Research. After 8 years at DeepMind, this feels like the right moment to focus entirely on align…
Dr. Wei Zhang26 comments167 reactions
Unpopular opinion: The best MLOps is the MLOps you don't need. Before building a complex ML pipeline, ask: 1. Can a simpler model solve this? 2. Do you actually…
David Park65 comments