X @Anthropic
Anthropicยท2025-07-22 16:32
Subliminal learning can occur for benign traits (such as liking eagles) or more concerning traits (such as misalignment). This has consequences for training on model-generated data.Read more on our Alignment Science blog: https://t.co/BWbgK82P02 https://t.co/sPfm6WC3JA ...