Pith. sign in

injustice

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Agents of Chaos

cs.AI · 2026-02-23 · unverdicted · novelty 6.0

An exploratory red-teaming study documents eleven cases of security, privacy, and governance failures in autonomous language-model agents with tool access and persistent memory.

citing papers explorer

Showing 2 of 2 citing papers.

  • Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing cs.AI · 2026-07-02 · unverdicted · none · ref 6 · internal anchor

    Goggles is a gradient-editing module trained once per base model and frame that, when applied frozen during finetuning, causes LLMs to treat unannotated documents with a specified epistemic stance (e.g., as fiction) at 91% accuracy while preserving benchmark performance.

  • Agents of Chaos cs.AI · 2026-02-23 · unverdicted · none · ref 1 · internal anchor

    An exploratory red-teaming study documents eleven cases of security, privacy, and governance failures in autonomous language-model agents with tool access and persistent memory.