ELK Results
1st Place: $15,000
Derik Kauffman • Andrew Gritsevskiy • Joe Cavanagh
For a proposal identifying direct translators by penalizing large changes in output given changes in data quality.
2nd Place: $5,000
Dylan Iskandar • Uzay Girit
For a proposal predicting the predictor’s
output given part of its initial state.
3rd Place: $2,000
Ethan Feldman
For a proposal extending the idea of penalizing excessive predictor activations by removing any random activations.
Honorable Mentions: $1,000 each
Jack Edwards, for an approach to distinguish translators from human simulators
Peter Berggren, for an approach utilizing a debate between multiple agents
Raymond Douglas, for a strategy penalizing the parts of a reporter that rely on human simulation
Ulisse Mini • Luke Bousfield, for a proposal drawing from shard theory, a novel idea in alignment research