Mflena

TL;DR: A read of the Claude Opus 4.8 system card with a focus on alignment assessment and construct validity of evaluation methods. Three main concerns: 1) chain-of-thought monitoring misses reasoning that never surfaces in the text; 2) evaluation awareness is under-estimated; 3) the evaluators come largely from the same model...

Introduction Automating alignment evaluation and research is thought to be an efficient way to safeguard against uncontrollable AGI, as Joe Carlsmith and Jan Leike themselves admitted. In particular, Leike proposed a Minimal Viable Product (MVP) for alignment, consisting in: > "Building a sufficiently aligned AI system that accelerates alignment research...