trends.barnas.net

phenomenon · first seen 8 Oct 2026

AI safety evaluation of model jailbreak robustness

Also: HarmBench, StrongREJECT

Measuring how inference optimizations alter a model's refusal and harmful-output behavior compared with its native baseline.

Mentions per week

0219 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

item response theorydifferential item functioningKV cache reuse