They summarize our coverage. We write it.
Newsletters like this one rebroadcast our headlines - often without the full review, the source reading, or the analysis underneath. Our weekly briefing sends the work they paraphrase, straight from the desk, before they get to it.
Free, weekly, no spam. One email every Tuesday. Unsubscribe anytime.
Anthropic accused Alibaba's Qwen lab of running 28.8 million unauthorized exchanges against Claude through 25,000 fake accounts, and urged Congress to tighten export controls on AI model access.
Alibaba launches three open-weight models for robot manipulation, navigation, and world prediction, built on a shared Qwen3.5 backbone with open weights.
Alibaba's generalist VLA model for robotic manipulation, built on Qwen3.5-4B with a DiT action decoder, trained on 38,100+ hours of open-source data, and ranked first on the RoboChallenge generalist track.
Alibaba's first multimodal agent model, combining GUI grounding (ScreenSpot Pro 79.0), 1M-token context, and text-plus-vision input at $0.40/M tokens.
Alibaba's agent-first flagship model with a 1M-token context window, topping Terminal-Bench 2.0 and SWE-Bench Pro at roughly one-sixth the cost of Claude Opus 4.7.
The state of open-source large language models in 2026 - who leads, how close they are to proprietary models, which licenses allow commercial use, and how to access them.
Chinese AI providers now handle over 60% of all tokens routed through OpenRouter, up from less than 2% just a year ago.
Qwen3-Coder-Next is an 80B MoE coding model from Alibaba that activates just 3B parameters per forward pass, scoring over 70% on SWE-Bench Verified with agent scaffolding under Apache 2.0.
Palisade Research shows frontier AI models autonomously exploit vulnerabilities and deploy working AI inference servers on remote machines, with success rates jumping from 5% to 81% in twelve months.
Three new papers reveal how agent memory silently breaks, how a tiered architecture recovers it, and how models can self-improve without human labels.
Qwen3.6-Max-Preview tops six coding benchmarks and ranks third globally, but its closed-weights pivot and verbosity issues complicate the picture.
Qwen3.6-35B-A3B lands with 73.4 on SWE-bench Verified and Apache 2.0 weights, all from 3 billion active parameters routed through a 256-expert MoE. Fits on a single consumer GPU.
