A Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models

Abstract

We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Anthropic, Fable 5 and Opus 4.8, against four families of automated jailbreak attack across 7 826 harmful intents spanning a ten-category harm taxonomy. Using the HackAgent red-teaming framework, hundreds of thousands of adversarial attempts were generated and every apparent success was independently re-adjudicated by a panel of three judge models (majority vote). Both models resist the majority of a

Categories

Framework mappings

Suggested from the entry's categories.

@misc{franco2026redteam,
  title = {{A Red-Team Study of Anthropic Fable 5 \& Opus 4.8 Models}},
  author = {Nicola Franco},
  year = {2026},
  month = jun,
  eprint = {2606.18193},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.18193}
}