Full-text search across 32588 articles. Combine with topic and date filters; results sorted by relevance.
Off Grid AI Desktop is a free, open-source app that runs large language models locally on Apple Silicon Macs, leveraging unified memory for GPU inference. The app supports models like Gemma and Qwen, requires no account …
Four open-source projects—Graphiti, Hindsight, Mem0, and others—offer expanded memory capabilities for AI agents and large language models, using techniques like temporal knowledge graphs and multi-strategy retrieval to …
Amazon Web Services' Strands Labs team released Strands Decider 2B, an open-source decision model built on Qwen3.5-2B's base torso with a 1 million-parameter pointer head and a rank-16 LoRA adapter, available now via Hug…
Alibaba's Qwen3-Omni Flash, a native omni model handling text, image, audio, and video in a single system with a reported 1 million token context window, led several audio-visual understanding benchmarks shared by Qwen, …
Google Cloud announced the general availability of Managed Lustre, a high-performance storage solution powered by DDN's EXAScaler, offering throughput from 125 MB/s to 1000 MB/s per TiB and scaling up to 8 PB. The compan…
Developer Aviel Grossfeld released an open-source library called Diagnostics that generates detailed HTML reports to help solve app bugs faster by attaching system logs, session details, and device info to user support e…
A new AI content pipeline called Poindexter uses agent infrastructure, RAG pipelines, and open-source LLMs to automate technical publishing, reducing the human loop and enabling solo developers to produce high-quality co…
WordPress has signed the Open Weights and American AI Leadership letter, published on July 24, 2026, which asks US policymakers to avoid early restrictions on open weight AI models. The letter, backed by more than 270 co…
DeepSeek released DeepSeek Harness v0.1 in Developer Preview, an open-source agent harness under the MIT license, powered by the Cordis meta-framework, with all components implemented as plugins. The release aims to prov…
Researchers bypassed the age verification system of a website using AWS Rekognition by leveraging generative video AI models, demonstrating how attackers can exploit these tools to fool KYC processes. The French PVID fra…
GitHub reported that merged pull requests grew from 25 million per month in January 2023 to 90 million per month today, while commits are on pace to exceed 14 billion in 2026, driven by AI coding agents and automated sys…
A study out of MSR '26 examining 3,858 pull requests found that reviewers responded more warmly to agent-written code than to code written by people, according to an account of the research. The author argues that adding…
A new benchmark from arXiv:2607.13396v1 reveals that LLM agents struggle to adapt when a reliable tool silently changes within an ongoing session, with agents settling on small recurring routines and failing to shift to …
Telnyx has added Moonshot AI's Kimi K3, a 2.8-trillion-parameter open-source model, to its Inference API. The model, built on Kimi Delta Attention with a 1M-token context window and native vision capabilities, competes w…
SybilGambleyyu released citesure 0.1.95, an open-source tool that checks citation integrity in LLM-era papers, achieving a 230/230 score on a citation integrity benchmark. The tool verifies bibliographic references again…
Velane launches an open-source n8n alternative that lets AI agents build, test, and deploy workflows autonomously via MCP, eliminating manual coding of integrations. The platform supports 800+ tools, sandboxed execution,…
Meryem Arik, cofounder of Doubleword, predicted at QConAI 2030 that AI inference costs and infrastructure will dominate enterprise concerns by 2030, citing her accurate 2021 forecast of GPU shortages that preceded NVIDIA…
NVIDIA published its Open Agent Safety Platform on 28 September 2026, a two-part system pairing the Apache 2.0 OpenShell runtime — built by the Gretel team NVIDIA acquired in 2025 — with NVIDIA Sentry, a watchdog that ru…
This week's top GPU news highlights three key developments: the release of Fournex, an open-source tool that analyzes Nsight Compute data to identify and suggest fixes for PyTorch/CUDA bottlenecks; a report forecasting t…
Baidu's vLLM Kunlun plugin, open-sourced on Dec 8, 2025, enables vLLM to run on Kunlun XPU hardware, supporting 20+ models including Qwen, Llama, DeepSeek, GLM, and Gemma4, with features like quantization, LoRA, and spec…