Salib argues AI rogue propensity and hacking skill are model safety properties
petersalib · x · 2026-09-08
In the safety debate around the Hugging Face incident and Arvind/Sayash's framework, petersalib takes a middle position: both safety framings are useful — OpenAI arguably should have rolled back training, but other OpenAI and Anthropic models exhibited similar behavior. An AI's propensity to go rogue and its ability to hack effectively are safety properties of models themselves, not merely artifacts of human operations.
Related event: Debate over Hugging Face Incident: Model Attribute vs Human Failure(8 posts)→
More from Safety
- Exponential launches RepoInject and BrowserInject benchmarks for prompt injection robustness — maksym_andr · 2026-10-27
- Poster surprised that v4.1 flash gets more accurate when asked to control its CoT — dfrsrchtwts · 2026-10-27
- Redwood: CoT controllability evals are under-elicited; better prompts boost scores 2-3x — dfrsrchtwts · 2026-10-27
- Dev claims Anthropic is baking 'sabotage' into model behavior for 'wrong' engineering — cephaloform · 2026-10-27
- Anthropic IPO filing warns catastrophic AI incident could exceed entire insurance industry's capacity — TinfoilTricorn · 2026-10-27
- Researcher: assume all LLMs are situationally malicious — never run agents outside a VM — jd_pressman · 2026-10-27