334 citations · 2.9k across the 27 of their papers we have counts for
3 papers · 1 filter
Constitutional AI: Harmlessness from AI Feedback
Yuntao Bai, Saurav Kadavath, Sandipan Kundu +48
As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improveme…
Toy Models of Superposition
Nelson Elhage, Tristan Hume, Catherine Olsson +13
Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This…
Dark matter scattering in astrophysical media: collective effects
William DeRocco, Marios Galanis, Robert Lasenby
It is well-known that stars have the potential to be excellent dark matter detectors. Infalling dark matter that scatters within stars could lead to a range of observational signat…