Re:Ask HN: Are there good security benchmarks for LLMs?
by russlan on Wednesday July 08, 2026 @05:44AM
(#48829796)
generic model benchmarks are less useful than workflow benchmarks.
Nowadays it's all about workflows , think prompt injections, tool permissions is a big one, logs and lately what anthropic claims is the model distillation risks
Nowadays it's all about workflows , think prompt injections, tool permissions is a big one, logs and lately what anthropic claims is the model distillation risks