xAI open sourced the Grok Build CLI and reset the weekly quota
After getting dragged for silently uploading repos, xAI open sourced the Grok Build CLI and reset the weekly quota.
github.com/xai-org/grok-build
xAI open sourced the Grok Build CLI and reset the weekly quota
More posts
Everyone's bearish on MiniMax because coding slipped.
But I've been running a general agent on vision stuff lately with M3, and it's surprisingly good. Other multimodal models are either expensive or bad. The cheaper ones aren't even native multimodal. M3 is the only one that gets all three right: price, quality, and native multimodal.
My friend just dropped real money on AI certs that are basically
fancy PDFs. The AI cert space is the wild west. No single recognized body, no industry standard. Just vibes and marketing. Here's the reality most companies operate on: if your AI stack is on a cloud, they want people who know that cloud. Three cert families actually move the needle. Google Cloud ($99 to $200): Cloud Digital Leader first, Professional ML Engineer after. Lives in the Gemini / Vertex AI world. Azure ($99 to $165): AI-900 gets you in, AI-102 levels you up. Enterprise muscle, Office ecosystem integration. AWS ($100 to $300): Practitioner for fundamentals, ML Specialty when you're serious. Widest coverage, default for cloud infra teams. Or just do OpenAI's free certs. The brand name alone beats any sketchy cert you'll find online.
Meituan shipped LongCat-2.5
. 1.6T params, ~48B active, native multimodal, aimed at long-horizon agents, trained start to finish on Chinese hardware. Images get quantized into multi-level discrete tokens, and that's where Visual Coding and 3D pick up. On the RL side, failed trajectories get turned back into verifiable training tasks. W4A4 inference, 43% faster prefill. Meituan's own evals put it between Claude Opus 4.8 and Opus 5.
SenseTime open-sourced SenseNova Loop-9B-Preview.
It stacks layers instead of parameters. The decoder has 32 layers, but layers 4 through 27 run twice with shared weights, so a forward pass does 56 layers of work while the checkpoint stays at 9B. Their own eval numbers: 71.38 on BIRD-Dev and 13.72 on AutomationBench, both above Qwen3.5-27B. Terminal Bench is still behind.
