2026-11-03 AI 日报

Computer use CLI for AI agents

Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical

将AI Studio Playground和Build反代成API | AI Studio to OpenAI, Anthropic & Gemini Compatible API

A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C,…

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context…

Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.

Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki…

Free, open-source RAW editor for Linux, Android, Windows and macOS. GPU-accelerated, non-destructive, with masks, HDR merge and local AI.

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Real-time long-video generation requires continuous output with consistent appearance and natural motion. Existing chunk-wise autoregressive methods face…

Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However,…

Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data.…

Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable…

Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary models limits research into further…

Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions to complete outcomes. We present…

Computer graphics is built on code. Large language model (LLM) agents can now generate graphics code and iteratively refine it through various feedback. This…

Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360^{circ} scene offers…

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research…

Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse…

My company is pretty paranoid about leaking IP to the frontier labs through prompts, so we've all been diligent about disabling data sharing in Codex/Claude…

Yesterday’s hot paper was Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights by Rikiya Takehi, Jayden Teoh, Alex Zhang,…

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that…

TL;DR We find that frontier LLMs are surprisingly good at natively reading and writing neural network weights, well past what we’d expect from humans or…

I created a an experimental deterministic LLM inference engine called Defer . When given the same prompt, model and parameters such as temperature and seed…

Quick math before picking a model or provider. An agent resends the whole session every turn. 100K context, 50 turns => 5M input tokens, almost all of it…

Saw the interactive DeepSeek-chan and the Codex pets going around and wanted one I could talk to, so I built this. She just hangs out on my desktop. Drag her…

I am seriously impressed and want to share my experience. Qwen3.8-Flash-Next (local) vs Claude in Claude Code: reviewing one real commit I ran the same code…

I like to decomp games, mod games, make clones of games and make new games. I pretty much exclusively use it for game related things. Some examples of what…

Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.

Per-token API prices keep falling, yet engineering bills for autonomous coding agents keep climbing....

How OpenAI built Pando, a Git-compatible backend designed for the scale of development that Codex makes possible.

Released GPT-6 Rosalind, bringing specialized biological reasoning with scientific tool use to complex life sciences research. Access is available to…

Discover how Heimstaden uses OpenAI’s ChatGPT Enterprise and Codex to transform property management, cut costs, and empower employees across Europe.

gemini-2.5-flash is deprecated and is no longer available to select in Google AI Studio. Effective December 1, 2026, all API requests to gemini-2.5-flash will…

Long conversations and agent loops on the Messages API can now send smaller requests and get a lower time to first token with message threads, in beta with…

The weights of Mistral Large 4 (Le Chonk) are now open. A 1T parameter multimodal model, and best open-weight model for coding, trained in Europe.

We’ve deprecated fast mode for Claude Opus 4.8, with removal on November 30, 2026. After removal, requests to claude-opus-4-8 with speed: "fast" will return…