PerspectivesOrdinary
本周最佳两篇 Week 26 Training a Misaligned Reward Seeker Steering towards "automated grading" degrades a…
Summary
This record preserves its title, category and source. Open the original source for full details.
CategoryAI Perspectives & Methods
TierOrdinary
Published
Indexed by AIQB
SourceX:马东锡 NLP (@dongxi_nlp)
AIQB record IDintel-cdeb0eebf51edc1c12b0b1cf