News
AI, cybersecurity, machine learning, scraping & programming news.
Show HN: Television – an open source GUI for your agent harness
A visual space for agent artifacts Television emerges as a dedicated interface layer between users and their autonomous agents. Where chat windows tend to scatter information across transient conversations, Television provides a p...
PTXBench: Benchmarking and Adapting LLMs for GPU Kernel Optimization
PTXBench evaluates LLM-generated GPU kernels on real hardware Genghan Zhang and collaborators introduced PTXBench in August 2026 as a benchmark for evaluating and adapting large language models to use architecture-specific PTX for...
Apple changes full-disk access permissions to curb abuse from AI agents
Apple tightens Full Disk Access to curb AI agent overreach Apple announced changes to macOS privacy settings intended to limit how third-party applications access sensitive user data. The update targets Full Disk Access, a system-...
Amazon writes scary blog warning communities not to block data centers
Amazon Web Services chief Matt Garman has published a extensive blog post urging communities to support AI data center projects, warning that opposition could inflict lasting damage on the US economy and national security. The mor...
Stages of grief about the effect of AI on open source
Denial: AI-generated code faces immediate resistance The first responses made clear that many developers remain skeptical about AI-assisted programming. Claims that AI-produced code amounts to slop spread quickly, with the asserti...
Embedding Prediction Helps Image Generation
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks,...
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
Author-Annotated Benchmark for Scientific Paper Retrieval ScholarCatalyst introduces a benchmark designed to study how researchers identify prior work that inspired their projects. The dataset was built by having 184 lead authors...
VISTA: A Visual Harness for Reasoning in an Interactive World
We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness that gives a...
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
Large language models now appear in security workflows where analysts expect them to turn natural language into exact tool invocations. Existing benchmarks test knowledge or end-to-end agent behavior, but they skip the core challe...
Cost-augmented Schrödinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control
The generalized Schrödinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. Previous work has approached this by learning the rates of a controlled continuous-time Markov chain...