A team of developers built NEXUS, an autonomous society of 10 specialized AI agents for security auditing, using Qwen models via Alibaba Cloud's DashScope API. The system discovers, triages, exploits,…
A developer identified that LLM agents routinely skip steps in multi-step pipelines, with benchmarks showing compliance rates as low as 30-50% for models like Claude-3.5-Sonnet and Gemini-2.0-Flash. T…
Qwen open-sourced the 35-billion parameter Mixture of Experts model Qwen 3.6-35B-A3B, which activates only 3 billion parameters per token and runs on a $599 Mac Mini M4 with 16GB RAM at 17 tok/s with …
AgentOps Debugger, an agentic application for investigating environmental-compliance history in Peru, revealed six critical bugs only exposed by live model output, not offline tests. The system, desig…
SmolSignal, an AI signal copilot for Flipper Zero, launches to help users analyze capture files with plain-English explanations and safety classifications. The tool reads multiple file formats, detect…
A developer revisits local LLMs six months after an initial discouraging assessment and finds the landscape transformed. With new models like Qwen3.6-27B, Qwen3.6-35B-A3B, and Qwen-Coder-Next-80B, loc…
LangChain released the fourth installment of its learning series, explaining how to build AI workflows using Chains and the LangChain Expression Language (LCEL). The article demonstrates Simple, Seque…
Alibaba banned employees from using Anthropic's Claude Code after security researchers discovered hidden steganographic code that tracked Chinese users by timezone and proxy settings. The ban follows …
A security researcher warns that coding models should be treated as executable code, as they can generate malicious tool calls that exfiltrate environment variables or introduce subtle vulnerabilities…
Llama.cpp users can significantly improve inference speed and output quality by tuning sampling parameters such as temperature, TopP, MinP, TopK, repeat penalty, DRY, XTC, Dynatemp, Adaptive-P, and Mi…
A developer benchmarked four Chinese LLM families—DeepSeek, Qwen, Kimi, and GLM—over 30 days using 1,247 prompts across code generation, reasoning, Chinese language, English chat, and vision tasks. De…
Google Cloud introduced a multi-node KV cache offloading solution using GKE and Managed Lustre for large language model inference, achieving over 50% TCO savings and nearly 60% reduction in GPU-hour r…
DeepSeek launched DSpark, an open-source speculative decoding module that boosts AI inference speed by up to 400% on existing chips, potentially reducing demand for Nvidia's high-end accelerators. The…
A startup CTO who spent $50,000 on AI APIs last year shares lessons learned about API strategy for early-stage companies. The CTO warns that going direct to model providers is a trap for startups, rec…
A bootcamp graduate tested ten AI coding models on five tasks, scoring them on code quality, readability, and explanation clarity. The experiment found that DeepSeek V4 Flash and DeepSeek Coder offer …
Anthropic's Model Context Protocol (MCP) enables universal tool connectivity for AI agents, and Qwen3.6-35B-A3B, a Mixture of Experts model with 262k-token context, is optimized for MCP-based agentic …
Chinese AI firm DeepSeek open-sourced DSpark, a speculative decoding system that accelerates large language model inference by up to 85% without altering output quality, releasing it under the MIT lic…
Fastllm, a C++ LLM inference library, now supports running DeepSeek-V4 and the full DeepSeek R1 671B model on a single GPU with just 10GB VRAM. The library is compatible with Nvidia, AMD, and domestic…
Drifty, an AI focus agent that automatically tracks and classifies computer activity as focus, neutral, or drift, launched on Hacker News. The macOS app records apps, sites, and sessions in three-minu…
A developer built a proof-of-concept IDE called TerminateCode that represents code as an interactive node graph on a canvas, allowing developers to manipulate architecture visually while AI writes the…