2026-10-08 AI 日报

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

Self-hosted gym & body-weight tracker — plan routines, log workouts (supersets, warm-ups, cardio), see which muscles are trained, fatigued or detrained,…

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Factory Droid, and Pi. 42 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid…

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

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

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

AI Agent Builder and Runtime by Docker Engineering

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

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

Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a…

Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with…

Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under…

Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience…

Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering…

Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision…

State tracking requires an update at every input, but the depth a Transformer applies to each token is fixed regardless of sequence length. We introduce the…

Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer…

Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions.…

Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction.…

https://github.com/openai/math/blob/main/history.md

Openai just launched their decisions endpoint, cloudflare launched clef the other week, and many more jev alternatives are out there. We wanted to put the…

Ultrafast is rolling out today for GPT-6.1 Sol in the API, Codex, and ChatGPT Work. Near-Astra intelligence at up to 8x faster speeds than Sol Standard, so…

We're deepening our commitment to scientific research and technological discovery by committing $150 million to the Genesis Mission. We'll also make Claude…

An astrophysicist worked with Claude Science to create the first complete ultraviolet map of the sky. Astronomers have already created complete sky maps from…

This hacker is truly legendary. A complete amateur. 1. He left directory listing enabled on his own server, so researchers could figure out who he was with…

Last week some of South Korea's biggest banks were hit by a cyberattack. Thanks to a report from CrowdStrike tonight, we now know the entire hack may have…

ChatGPT launched their version of Generative UI yesterday. We took it apart tldr; the agent never write raw code. It emits DIL (a new language), the server…

I spent $0.22 USD on DeepSeek Flash 4.1 tokens and achieved something that a few years ago would have required days of manual work: creating a 3D character,…

Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models…

We test three state-of-the-art multi-modal large language models (GPT-4o, Gemini-1.5-Pro, Gemini-1.5-Flash) and find that they fail dramatically when…

text-to-image

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

automatic-speech-recognition

text-classification

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,…

Anthropic is committing $150 million over three years to the Genesis Mission, a federal initiative to accelerate scientific and technological discovery…

Brice Ménard, an astrophysicist at Johns Hopkins University and a researcher at Anthropic, explains how he worked with Claude Science to produce the first…

The deep-research-pro-preview-12-2025 agent is deprecated and will be shut down on October 23, 2026. Migrate your requests to one of the newer Deep Research…

gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. All requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash.…

gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. All requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash.…