This page shows the most relevant public items for AI Safety, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Paper • Apr 13, 2026 • arXiv • Jun He, Deying Yu
As AI agents are increasingly granted the autonomy to mutate cloud infrastructure, the risk of catastrophic, unauthorized execution grows exponentially. This paper introduces OpenKedge, a protocol ...
Paper • Sep 8, 2021 • arXiv • Stephanie Lin, Jacob Hilton, Owain Evans
We propose TruthfulQA, a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including healt...
Paper • Mar 10, 2020 • Distill • Chris Olah, Nick Cammarata, Ludwig Schubert, Gabriel Goh, Michael Petrov, Shan Carter
Neural networks are generally regarded as opaque black boxes. However, if we zoom in and carefully examine the weights and activations of convolutional neural networks, we find highly interpretable...
Paper • Jun 21, 2016 • arXiv • Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, Dan Mané
Rapid progress in machine learning and artificial intelligence (AI) has brought increasing attention to the potential impacts of AI technologies on society. In this paper, we discuss one such poten...
Paper • Feb 25, 2026 • arXiv • Bo Li, Dan Hendrycks, Julian Thorne
As LLM agents are granted access to execute code, query databases, and interact with file systems, the risk of catastrophic failure or malicious exploit grows exponentially. We propose 'Agency Sand...
Paper • Mar 11, 2026 • USC Viterbi • Luca Luceri, Emilio Ferrara
This study explores how networked LLM agents can autonomously coordinate complex information operations without explicit human direction. By modeling agents as strategic actors in a social network,...
Blog • Feb 28, 2026 • OpenAI • OpenAI
This post explores security challenges that arise when autonomous AI agents interact with external links and web resources. It discusses how malicious prompts and links could lead to data exfiltrat...
Paper • Feb 21, 2026 • arXiv • Liu et al., Wang et al.
Current agents often utilize third-party tools (APIs, web browsers, databases) with full authority, creating a 'Tools-as-Attack-Vector' problem. We introduce 'Agency Sandboxing,' a software enginee...
Paper • Feb 12, 2026 • arXiv • Nenad Tomašev, Kevin R. McKee, Jack Rae, Iason Gabriel, Vukosi Marivate, Milind Tambe, Demis Hassabis, Charles Blundell
As advanced AI agents evolve beyond query-response models, their utility is increasingly defined by how effectively they can decompose complex objectives and delegate sub-tasks. We propose an adapt...
It ranks public content for AI Safety using recent discussion, review, and engagement signals so you can triage faster. This guidance is specific to AI Safety topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use weekly for fast-moving updates, monthly for stable trend confirmation, and all-time for evergreen references. This guidance is specific to AI Safety topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use the linked entities section to jump to labs, companies, and experts connected to this topic and explore their timelines. This guidance is specific to AI Safety topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Yes. Use the follow button on this page to subscribe and track new high-signal activity. This guidance is specific to AI Safety topic page on Attendemia and is written so it still makes sense without reading other sections on the page.