Papers worth coming back to.

Research papers repeatedly shared on Hacker News. Follow the ideas that last.

1,237 papers · At least 3 readers across 3 monthsThe method

Historical snapshot through August 2026. Rule-labeled recommendations.

Sort by

Loading full catalog… in Security & cryptography

2025arXiv

Design Patterns for Securing LLM Agents against Prompt Injections

Luca Beurer-Kellner, Beat Buesser, Ana-Maria Creţu +11

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge.

Security & cryptography Language models

4 mentions4 months

2.5HN score

2019arXiv

Spectre is here to stay: An analysis of side-channels and speculative execution

Ross Mcilroy, Jaroslav Sevcik, Tobias Tebbi +2

The recent discovery of the Spectre and Meltdown attacks represents a watershed moment not just for the field of Computer Security, but also of Programming Languages.

Security & cryptography Programming languages Mathematics

18 mentions14 months

2HN score