2026-10-27 AI 日报

A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser…

A high-performance inference engine for AI models

Auto Ontology is a Python framework for building semantic, graph-based reasoning layers over data. It enables deterministic query generation, better context…

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

The design vocabulary for your coding agent. Steer with polish and bolder, review with critique and audit, catch AI slop before it ships.

A collection of AI agent skills for working with Expo projects and Expo Application Services

Consider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

📨 The ultimate agentic social media scheduling tool 🤖

Universal SEO skill for Claude Code. 26 sub-skills + 19 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, agent readiness (Lighthouse Agentic…

Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements. We introduce DynaFlow, a…

LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support…

As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools,…

People have long dreamed of an assistant that is always there to guide them and remind what they forget, from new dishes to lost keys. Powered by multimodal…

Successful tool-use trajectories are not necessarily useful supervision. Even successful interactions may underrepresent multi-step dependencies or contain…

Critic-free methods are widely used in reinforcement learning with verifiable rewards (RLVR) for long chain-of-thought (CoT) reasoning, avoiding difficult and…

Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct…

Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined…

Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on…

Spatial audio authoring coordinates source decisions with soundfield synthesis. For editing, plans specify what to change and retain, while reference audio…

Genie 4 introduces real-time interactive world simulation with native audio, advanced physics, natural human motion, and steering powered by Gemini models.

Anthropic’s life sciences team is working to accelerate curing disease. Over the past several months, our scientists have engaged in deep research…

We are expanding our partnership with the General Services Administration (GSA) through a new agreement that gives government partners a 40% discount on…

Implemented agent smith since start 2026 with over 1000 specifications which lead to about 500k lines of code. The procedure with that spec-first works well.…

Announcing Artificial Analysis Intelligence Index v5, featuring 2 new benchmarks and 3 upgrades. For the first time, the majority of the Index is built on…

https://huggingface.co/LiquidAI/LFM3-1.7B-GGUF from liquidAI: LFM3-1.7B is a text model for local agents and specialized applications, based on our new…

ok to put what i'm saying about demand in context openrouter is the most successful model router, you can almost serve 100% of their deepseek traffic…

Chain-of-thought transformed AI reasoning, but it is limited to words. What's the physical-world analogue? Introducing Ψ-0.6, one model that reasons in…

I think a turn of events are pointing towards a very likely crash in prices in the coming months. With a single gb300 rack being to serve all of Openrouter's…

Papers with Code is now open-source with an Apache 2.0-license. The goal is to collaboratively create the best paper interface with the community! Over the…

HF traces: https://huggingface.co/datasets/CohereLabs/10-2026-qwen-investigation-traces 1. Understand the Python script: ids ids = dataset[0]["token_ids"] if…

I’ve uploaded a minimal, self-contained implementation of manual autograd for a transformer-based classifier in PyTorch. It can help build intuition for what…

Your OCR says it’s done—but did it get everything right? 🤔 In high-stakes workflows, even a small error can be costly. 🚀 Meet the MiniCPM-OCR suite: an…

Genie 4: our new world model unlocking unprecedented realism in real-time simulation.

You can now set content guidelines on text API requests. Add a guidelines array to a Chat Completions or Responses API request to set how Grok handles content…

CodeRabbit uses GPT-6.1 Sol to investigate security risks across complex codebases. Its security agent helps developers review findings and proposed fixes.

OpenAI shares model results on the Kakeya conjecture, Exponential Time Hypothesis, and quantum chromodynamics—and how researchers can verify and build on them.

Released the Gemini API CLI (gemini-api), a stateless, zero-dependency command-line client for AI coding agents, scripts, and CI pipelines. Use gemini-api on…

With OpenAI Daybreak, Check Point speeds up the research behind new security protections, enabling its analysts to turn vulnerability intelligence into…

A2UI now supports swappable inference formats, introducing A2UI Express which uses up to 3x fewer tokens and cuts latency by compiling compact Python-style…

Z.ai GLM 5.3 Flash (zai-glm-5-3-flash) is now available. A multimodal 320B-parameter (18B active) Mixture-of-Experts model from Z.ai with a 1M-token context…