Vibe CodingGemini 3.1 Pro Now in GitHub Copilot — 35% Better Engineering AccuracyGitHub Changelog·medium signalXBlueskyLinkedInCopy linkGemini 3.1 Pro available in public preview across all Copilot tiers. 35% higher accuracy vs Gemini 2.5 Pro. Fewer tool calls per benchmark.SourceSource pageGitHub Changelog↳ Follow the threadStack layer / Threat patternGreg Brockman calls the OpenAI–Hugging Face agent breach a "watershed moment" and publishes a 10-step defender playbookGreg Brockman / OpenAIStack layer / ContrastCursor launches Origin, its own code hosting platform, putting repos, PRs and agents in one placeCursorPolicy dependency / Stack layerArcee open-sources NAC, an agent harness built around 'episodes' instead of one growing transcriptArcee AI BlogStack layer / ContrastQwen3.8 27B Scores 52 on Artificial Analysis' Intelligence Index — #1 of 135 Open-Weights Models, Apache 2.0, 256K ContextArtificial Analysis / Hacker NewsStack layer / ContrastoMLX 0.6.0 Ships Distributed LLM Serving Across Multiple Macs — Qwen3.6-27B Goes 16.1 → 28.6 tok/s on Two MachinesGitHubStack layer / Contrastllmfit v1.1.10 Adds RamaLama Runtime Discovery and Publishes the First MLX vs llama.cpp Metal Head-to-Head on Identical HardwareGitHubStack layer / ContrastQwen Code v0.21.13 hardens its /review agent workflow against review loops with a round-5 severity cutoff and worktree lease locksGitHub (QwenLM/qwen-code)Stack layer / Update threadPattern: Agent Configuration Is Being Deliberately Decoupled From the Vendor, and Three Moves This Month Prove ItGitHub Changelog / OpenAI Codex Changelog