Full-text search across 17293 articles. Combine with topic and date filters; results sorted by relevance.
A study of 159 software developers found that Google's Gemini AI tool did not significantly improve code security compared to using no AI assistance. The research, conducted by Nadine Jost, showed that developers' progra…
Researchers have developed Reasoning in Memory (RiM), a latent reasoning method that replaces the autoregressive generation of intermediate reasoning steps with fixed memory blocks processed in a single forward pass. The…
A developer built a GitHub Stats MCP Server that integrates CHAOSS security metrics to assess open source project health. The server uses five tools aligned with the CHAOSS Security Practitioner Guide, including a Libyea…
Researchers have developed Agent-Radar, a training-free context management method that dynamically steers each agent's attention toward relevant information using a temporal and spatial decay mechanism. The method addres…
Researchers have developed Memory-as-Action (MemAct), a framework that treats working memory management as learnable policy actions for large language models, enabling joint optimization of information retention and task…
A Netflix engineer developed Project Headroom, an open-source application designed to reduce the cost of running large language models by optimizing GPU memory usage. The tool, which the creator released publicly, aims t…
A developer in Tokyo conducted a 30-day structured benchmark of four Claude models in Claude Code, tracking token usage, response quality, and cost per task type. The results contradict the consensus that Sonnet 4 is the…
A developer has published a new book, "Web Automation with Playwright and Python using AI and MCP," now available on Amazon worldwide. The book covers end-to-end test automation, API testing, visual testing, and AI-power…
Researchers have developed a conditional scaling law that predicts optimal large language model architectures for inference efficiency, training over 200 models from 80 million to 3 billion parameters. The study found th…
OpenAI announced that an internal AI model produced a proof resolving the planar unit distance problem, a geometry conjecture posed by mathematician Paul Erdős in 1946. Mathematicians including Timothy Gowers and Daniel …
Researchers have demonstrated the first autonomous worm capable of propagating across multiple large language model agent frameworks without human interaction, using persistent agent memory and scheduled task states to r…
Millville, New Jersey city commissioners voted to ban data centers within city limits, blocking a proposed 2.6-million-square-foot facility. The decision, hailed by opponents as the largest data center project halted in …
Large language models are beginning to outperform human forecasters, with AI expected to rival superforecasters on most questions by next year. Despite decades of proven ability to produce well-calibrated forecasts, the …
Researchers introduced Effective Feedback Compute (EFC), a new scaling coordinate that measures only informative, non-redundant feedback in AI agent harnesses, outperforming raw-compute metrics in predicting failure rate…
Anthropic surpassed OpenAI to become the world's most valuable AI startup at a $965 billion valuation, driven by enterprise adoption of Claude Code. The proliferation of AI coding agents continued with new open-source to…
Anthropic released Claude Opus 4.8, a model that flags its uncertainty more readily and is roughly four times less likely to let code flaws slip by unremarked. The release comes as industry leaders argue that AI sharpens…
Researchers have developed Cassandra, an algorithm-hardware co-designed self-speculative decoding framework that enables lossless acceleration of reasoning large language models on edge devices without additional trainin…
Researchers have developed StoryScope, a pipeline that analyzes discourse-level narrative features to distinguish AI-generated fiction from human-written stories without relying on stylistic cues. Testing on a corpus of …
Researchers introduced Diffinity, a training-free guidance method that enables continuous diffusion language models to satisfy formal syntactic constraints defined by regular expressions. The method constructs an analyti…
A new study from researchers has systematically measured behavioral consistency in multi-step tool-calling LLM agents, finding that the same agent often fails to select the same tools, in the same order, or with the same…