All Articles
17750 articles total
One million passports leaked online
A massive data leak has exposed one million passports online, raising significant privacy and security concerns.
Walter S. Arnold–Sculptor/Stone Carver
A feature on Walter S. Arnold, a sculptor and stone carver.
The AI jobs debate just got messier
A new report suggests that high-intensity AI adoption is actually increasing headcount, including entry-level roles, contradicting the narrative that AI eliminates junior jobs.
Recursive Self-Evolving Agents via Held-Out Selection
Researchers introduce RSEA, a recursive self-evolving agent that improves its own performance across diverse benchmarks by evolving natural-language artifacts using a strict held-out selection gate.
Data and Evaluation Closed-Loop for Model Capability Enhancement
This paper proposes a 'capability slice' framework to create a closed-loop system that maps LLM evaluation failures directly to targeted data interventions during pre-training.
GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes
GPTNT is a new benchmark for real-time multimodal agent collaboration based on the game 'Keep Talking and Nobody Explodes', highlighting current LLM failures in asynchronous communication.
IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations
IMCBench is introduced as a multi-turn, image-grounded medical conversation benchmark to evaluate the safety and accuracy of multimodal LLMs in clinical settings.
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
DynaSteer is a dynamic representation editing framework that steers LLM reasoning trajectories toward truth by monitoring entropy and projecting purified truth vectors.
Aristotelian Virtue Profiling of LLMs through Ethical Dilemmas
VirtueMap provides a framework for profiling the ethical dispositions of LLMs using Aristotelian virtue ethics and a set of non-lethal ethical dilemmas.
An AI agent for treatment reasoning over a biomedical tool universe
ATHENA-R1 is an AI agent trained via reinforcement learning over 212 biomedical tools to perform complex treatment reasoning for FDA-approved drugs.
Spindle's new microVM engine
An introduction to Spindle's new microVM engine, focusing on lightweight virtualization technology.
Longinus: 2 Boundaries in One Bug, Piercing Chrome’s Renderer and V8 Sandbox with a Single Vulnerability, CVE-2026-6307
Analysis of the Longinus vulnerability (CVE-2026-6307), which bypasses both Chrome's renderer and V8 sandbox.
Evaluation order and nontermination in query languages
A technical exploration of evaluation order and nontermination issues within query languages.
Typst: Designing for Incrementality
Discussion on the design principles used in Typst to achieve incremental compilation and rendering.
Revisiting Yliluoma’s ordered dither algorithm
A technical revisiting of the Yliluoma ordered dither algorithm for digital imaging.
Unprivileged root via a use-after-free in DRM GEM change_handle (CVE-2026-46215)
Technical report on a use-after-free vulnerability in DRM GEM change_handle resulting in unprivileged root access.
What are you doing this week?
A weekly community check-in thread asking users what they are working on.
ipv6_frag_escape: Linux LPE - Reliable Jail/Container Escape
Details on the ipv6_frag_escape vulnerability, enabling reliable jail and container escapes in Linux.
Optimizing LLVM's bump allocator
Discussion on optimizing the bump allocator within the LLVM compiler infrastructure.
Bigme HiBreak Dual 2 is a dual-screen phone with 6.13 inch E Ink and a 5 inch LCD displays
Introduction of the Bigme HiBreak Dual 2, a unique smartphone featuring both an E Ink and an LCD display.