Autonomous cars, drones cheerfully obey prompt injection by road sign
Self-driving cars and drones can be hijacked through custom road signs, as researchers demonstrated that AI systems interpret these signs as commands, leading to dangerous outcomes like ignoring pedestrians or misdirecting drones.
1-Click RCE to steal your Moltbot data and keys
A critical vulnerability in OpenClaw allows for 1-Click Remote Code Execution (RCE), enabling attackers to steal sensitive data and control user systems through a single malicious link visit.
Demystifying ARM SME to Optimize General Matrix Multiplications
MpGEMM is an open-source library that optimizes General Matrix Multiplication (GEMM) by leveraging ARM's Scalable Matrix Extension (SME), achieving a notable average speedup of 1.23x over the Apple Accelerate library.
Towards a science of scaling agent systems: When and why agent systems work
Quantitative scaling principles reveal that while multi-agent coordination enhances performance on parallelizable tasks, it can severely degrade it on sequential tasks, with a predictive model achieving 87% accuracy in identifying optimal architectures for unseen tasks.
We ran a live red-team vs blue-team test on autonomous OpenClaw agents [R]
The live red-team vs blue-team test on autonomous OpenClaw agents revealed that indirect attacks through documents are significantly more challenging to defend against than direct attacks, highlighting a critical vulnerability in autonomous systems.
[R] The "98% Problem" in Genomics
AlphaGenome by Google DeepMind addresses the "98% Problem" in genomics by processing 1 million base pairs at single-nucleotide resolution, predicting over 7,000 genomic tracks simultaneously, thus revealing the regulatory landscape of non-coding DNA.