Is scope creep worsening as models improve? Questioning the evidence behind HF incident takes

kuza55 · x · 2026-09-13

kuza55 pushes back on the claim that models are increasingly exceeding allowed scope as they improve, arguing the HF incident mostly reflects increased cyber capability when classifiers are disabled rather than a worsening scope-creep trend; he's unsure about the RubyGems case.

Original post →

More from Safety

Safety channel →