Full-text search across 33183 articles. Combine with topic and date filters; results sorted by relevance.
Goloop, an open-source agentic loop tool for the terminal, uses a supervisor/worker split where a planner never touches files and a dedicated worker performs all edits. The tool, available as a single static binary under…
A causal study of 151 open-source Java repositories found that agentic AI adoption increased code volume by 12.8% while leaving total architectural smells essentially unchanged, causing architectural smell density to dec…
Researchers introduced Pythagoras-Prover, a family of compute-efficient Lean theorem provers that achieve state-of-the-art performance with significantly fewer parameters. The 4B-parameter model surpassed DeepSeek-Prover…
Researchers have developed ToolSense, an open-source diagnostic framework that automatically generates three benchmarks to audit whether large language models truly understand their parametric tool knowledge. Testing on …
MandoCode, a new open-source AI coding agent built on .NET and Ollama, launched today as a local-first alternative to cloud-based assistants. The tool, which requires no API keys and runs entirely in the terminal, can re…
The MADSys Lab at Tsinghua University’s KTransformers project enables frontier-class MoE models like DeepSeek-R1 671B to run on commodity hardware with a CPU-GPU hybrid inference stack, achieving 286 tokens/s prefill on …
COOCON joined the Agentic AI Foundation (AAIF) as a Silver Member on June 1, planning to participate in working groups on AI agent payments and data businesses built on the Model Context Protocol. AAIF, an open-source co…
Anthropic's Claude Fable 5 scored 72% on SWEBench Pro, outperforming OpenAI's GPT 5.5 at 68% in real-world bug-fixing and feature implementation tasks drawn from major open-source repositories. The models also diverged o…
Xiaomi released MiMo Code V0.1, an open-source AI coding agent, on June 11 under an MIT license, achieving an 86.7% score on Terminal-Bench 2.0 compared to Claude Code's 65.4% on tasks exceeding 200 steps. The agent, pow…
GKE Labs has launched OpenRL, an open-source, self-hosted training API for fine-tuning large language models on Kubernetes. The API decouples post-training infrastructure from reinforcement learning research workflows, u…
An arXiv preprint submitted 23 Oct 2025 evaluates a topic-aware, hierarchical summarization pipeline that applied Latent Dirichlet Allocation to 50 transcribed stories from African American storytellers, identifying 26 t…
Bifrost, an open-source AI gateway written in Go, can handle thousands of concurrent LLM requests on Kubernetes with only 11 microseconds of overhead per request at 5,000 requests per second. The gateway demonstrates 54 …
AMD engineers are preparing open-source graphics driver support for a new GFX1156 graphics IP block in Mesa 26.2, which falls under the RDNA 3.5 "refresh" lineup as a future APU part. The GFX1156 is not a Strix Point var…
A developer built a 340-million-parameter vintage LLM from nearly scratch, training it exclusively on texts from before 1900 using custom scripts and datasets. The open-source model, available on HuggingFace, is time-loc…
Google Cloud announced the general availability of Lightning Engine for Managed Service for Apache Spark, delivering up to 4.9x faster performance than standard open-source Spark and 2x the price-performance over leading…
Amazon Web Services released an open source Nova Sonic Test Harness that enables automated testing of voice agents without requiring a microphone. The framework runs multi-turn conversations with Amazon Nova Sonic, evalu…
A developer built Wasla, an open-source synchronization layer that unifies AI coding assistants by syncing agent instructions and MCP servers across tools like Claude Code, Gemini CLI, and Cursor. The system runs locally…
Airbnb CEO Brian Chesky has launched a new, standalone AI lab to develop proprietary models focused on consumer-facing design and interaction, marking a strategic shift away from external AI providers. The venture, repor…
A developer compiled a list of 10 open-source GitHub repositories that collectively replace over $123 per month in paid developer tools, including alternatives to Zapier, Calendly, and DocuSign. The repos, such as Ollama…
Mira Murati, CEO of Thinking Machines Lab, made her first major public appearance in 18 months during a Bloomberg interview, previewing the company's "interaction models" that process continuous streams of audio, text, a…