PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address.

Keryn Headlines

Daily, Monday 8 December 2025 · Retrospective · Covers 7 December 2025 00:00 to 8 December 2025 00:00 UTC

Read on the web

Top developments

A Technical Policy Blueprint for Trustworthy Decentralized AI

arXiv · Research · Trust

SoK: Trust-Authorization Mismatch in LLM Agent Interactions

arXiv · Research · AI Security

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models

arXiv · Research · Models

Models

Graph-Regularized Sparse Autoencoders for LLM Safety Steering

arXiv · Research · Models

AI Security

SIEVE: Selective Integrity Verification and Escalation for Defending LLM Agents against Indirect Prompt Injection

arXiv · Research · AI Security

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.