Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning

Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning. The story centres on Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.