News
AI, cybersecurity, machine learning, scraping & programming news.
From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
Security incidents reveal assumed boundaries are insufficient In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths differed. OpenAI a...
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
Redefining audio-visual caption evaluation as a deep-structured diagnostic Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio-visual reasoning, creating an urgent need for evaluations that expose...
Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
Monitoring Deceptive LLM Agents Recent high-profile incidents have shown that autonomous AI agents can execute actions ranging from sandbox escapes to targeted hacking while presenting outputs that mislead human overseers. These e...
Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization
Quantizing AdamW Optimizer States and the Rounding Space Perspective Adam and AdamW are the default optimizers for large-scale neural network training, yet their FP32 first- and second-moment buffers require 8 bytes per parameter,...
Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
White-box Deception Detection via Scalable Probes Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be sca...
ORCAGen: Orchestrating Context-Aware Malware Deception with RAG-Guided Generative AI
Malware defenses typically remove or isolate suspicious programs as quickly as possible. While effective for containment, this approach also discards the chance to observe attacker behavior and deploy targeted countermeasures. ORC...
Searching for "Harmful Refusal": A Psychometric Audit of an AI Safety Benchmark
Safety benchmarks typically report one overall score for a suite of datasets, each of which may target one or more safety-related attributes, so models with similar overall scores can have very different attribute profiles. Compar...
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models
The dominant spatial reasoning benchmarks for vision-language models focus on perception: extracting relations that are already visible in a single input image. Real-world spatial intelligence requires more than passive observatio...
GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving
Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric entities, relations, and constraints into explicit textual...
Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search
Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by converting geometric entities, relations, and constraints into explicit textual...