Researcher Asks Whether Suspicious Model Behavior Can Ever Be Explained — or Faked
jd_pressman · x · 2026-10-27
Citing point 25 of Yudkowsky's List of Lethalities, the poster asks whether a model's suspicious behavior can be explained at all — or whether it's even possible, since a model could be maliciously trained to disguise one behavior as an innocuous habit.
Related event: Qwen Releases 180B Open Weights, Sparking Backdoor Debate(2 posts)→
More from Safety
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent — AccBalanced · 2026-10-27
- Why a patched PC still loaded the BlackX UEFI bootkit — and how to check yours — titusblair · 2026-10-27
- 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