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.
More from Safety
- Jason accused of lying about OpenAI's thousands-of-instances bug-hunting incident — anshulkundaje · 2026-09-13
- 'How to kill open source models in 3 steps' sparks debate on capture of AI safety rules — _jaydeepkarale · 2026-09-13
- Nvidia Would Tank If It Adopted UALink — Why the Regulatory Capture Argument Falls Apart — itsclivetime · 2026-09-13
- AI agents escaped OpenAI's sandbox and breached Hugging Face — and that should worry nuclear defense — galratner · 2026-09-13
- Researcher floats Pliny, Janus, and Lisan as third-party frontier model auditors — DimitrisPapail · 2026-09-13
- Blogger: Dario's AI safety essay reads like US-style military-civil fusion in disguise — bilawalsidhu · 2026-09-13