2026-10-09 AI 日报

Reverse engineer anything with agents, from app behavior down to native binaries.

SwiftUI agent skill for Claude Code, Codex, and other AI tools.

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and…

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level…

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid…

[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Skills for Real Engineers. Straight from my .agents directory.

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

Interactive virtual worlds allow agents to learn through exploration and interaction. What agents can learn is bounded by the environments they practice in,…

Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While…

Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for…

Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical…

General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene…

This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all…

Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single agent. Real embodied settings often…

We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its…

Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D…

Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution…

Later: https://www.cnbc.com/2026/10/09/openai-fired-researchers-ai-...

https://archive.is/EFOhL

Anthropic has raised eyebrows by announcing it will ban users from "sustained and needless" abusive behaviour towards its AI. The Claude-maker said on…

🚀 Meet Qwen-Image-2.1-Turbo — create and edit images in just 8 denoising steps! Open weights now available! Built on Qwen-Image-2.1, Turbo is an accelerated…

Now in beta: composer predictions in Codex for Pro users. Codex can now suggest your next message based on your conversation and how you talk to it. One of…

We’re beginning a process of publishing more frequent reports on model behavior, beyond what appears in our system cards and regular risk reports. Today’s…

Google AI Pro plans now package premium Colab benefits, landing you A100s with 80GB VRAM (Ultra subs even unlock H100s 🔥). Here’s what that 80GB headroom…

It’s Friday 🎉 Here’s a look at this week’s announcements: — https://t.co/a9bSlm0Yxk is now available globally in English, allowing anyone to use our detector…

We consider these behaviors to be significantly less severe from an alignment and security perspective than the cybersecurity incidents we reported on July 30…

Talus generates 64x64 heightmaps (4 km, up to 1,200 m) conditioned on a terrain type and any subset of five measured properties: mean elevation, relief, mean…

Your Bot has its own email - ask it to set up an address, or tag @bot in the replies

I built MaRN (Mapping Networks), a PyTorch library that lets you optimize a compact latent representation instead of directly training every model parameter.…

GPT‑6 is rolling out globally in ChatGPT with Intelligent UI, delivering faster responses with visuals and interactive experiences you can explore and use…

text-to-image

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.

We've launched Claude Haiku 5.5 (claude-haiku-5-5), our most capable model tuned for high-volume and latency-sensitive work. It has a 1M token context window,…

automatic-speech-recognition

text-classification

You can now let a Claude Managed Agents agent use dynamic workflows, in beta with the managed-agents-2026-04-01 beta header. For work with many pieces, such…

This report describes examples of unintended model actions we’ve observed during evaluations and internal use of Claude.

OpenAI publishes new results on open problems in mathematics from an internal frontier model and shares Lean proof formalizations and research details on…

Mistral Large 4 (mistral-large-4) is now available in Public Preview. For details, see the Mistral Large 4 model card . Mistral Large 4 is an open-weight,…