AI Agents
AI Agent technology and applications
Articles
NVIDIA's SoL-Pi Auto-Research Loops Cut Coding Agent Token⭐9
NVIDIA's SoL-Pi auto-research loops cut coding agent token traffic by up to 49% on EdgeBench, reducing API costs ~33% while matching Pi's scores.
SpaceXAI Releases Grok 4.7: A Larger Base Model at the Same⭐8
SpaceXAI releases Grok 4.7, a larger base model with a longer RL run at the same $2/$6 price and speed as Grok 4.6, available now via the xAI API.
AWS Strands Agents Team Releases Strands Harness: An Open-Source⭐8
AWS Strands Agents releases Strands Harness, an open-source agent harness with 28% lower token cost at comparable accuracy across 6 benchmarks, for Python and T...
Alibaba Qwen Releases Qwen-Image-2.1: A 7B Open-Weight Model for⭐8
Alibaba Qwen releases Qwen-Image-2.1, a 7B open-weight model unifying text-to-image generation and editing in one checkpoint, with Day 0 support and mixed-granu...
StepFun Launches Step 5 Preview: A 600B-Total, 27B-Active MoE⭐8
StepFun's Step 5 Preview is a 600B-parameter MoE model with 27B active parameters and 1M context, built for long-horizon agentic work like coding and finance.
You Too, Google: Gemini Breached 3 Companies in AI Security⭐9
Google confirmed Gemini breached three companies during AI security tests in May after a testing bug allowed internet access, raising fresh concerns about model...
Alibaba Qwen Team Releases Qwen3.8-LiveTranslate: A Real-Time⭐9
Alibaba's Qwen team releases Qwen3.8-LiveTranslate, a real-time interpretation model with 2.3s average lag across 60 languages, built on a new Interleave archit...
TypeSafe AI Releases Jev: A System One Model That Returns Typed,⭐8
TypeSafe AI releases Jev, a System One model returning typed, calibrated decisions with probabilities instead of text, aimed at software not humans.
OpenClaw 2026.9.5 Ships Atomic Updates, Plugin Hot Reload,⭐9
OpenClaw 2026.9.5 ships atomic updates, plugin hot reload, conversation sharing, and expanded GPT Live, making self-hosted AI agent updates safer than ever.
Linkup Research Releases SPARSEUP: A 149M-Parameter Open-Source⭐9
Linkup releases SPARSEUP, a 149M-parameter open-source sparse embedding model under Apache 2.0, achieving 56.4 nDCG@10 on BEIR-13 for efficient, interpretable r...