2026-10-19 AI 日报

DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐ 如要二开，请查看署名要求部分

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.

Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid…

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep…

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers.…

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Orca is the place for working with a fleet of agents (e.g. Grok Bot, Claude Code). Run any coding agent with your own subscription. Available on desktop,…

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive…

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and…

Recent closed-source image generation systems can produce diverse visual content from simple compositions to information-dense graphics, yet open-weight…

GPT-6-Astra demonstrates a level of competence in robotic manipulation and navigation that challenges the conventional paradigm of building specialized models…

Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards. We ask how far a coding agent can go when…

Existing long-horizon agent benchmarks often emphasize final task success while providing limited assessment of intermediate execution validity. Yet…

Can AI agents carry out research on open scientific problems? We introduce Into the Unknown, a benchmark that provides an agent with a science paper along…

Peer review is under strain from the growth of submissions, and review comments written by humans or AI can misstate what a paper says. We introduce…

Decision models answer typed questions about an input with one probability per option, computed in a single forward pass without generating text. Like the…

Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where…

Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This…

Interactive video generation commonly relies on small bidirectional chunks to reduce response latency. Yet our preliminary experiments show that larger chunks…

Timestral, Mistral’s first family of time-series foundation models, delivers state-of-the-art probabilistic, multivariate forecasts with just 209M parameters,…

https://public-inspection.federalregister.gov/2026-21447.pdf

Welcome back. Space Bunny. 🚀 MiniMax-M3.1-Flash is coming. https://t.co/geIOTBBLRr

Our latest model advances bring stronger capabilities for building and migrating software in low-resource programming languages such as COBOL, Fortran, and…

Hey guys, Nick here from Cohere. It's been a minute. We had a great time launching Command A+ and beta-testing North Mini Code with you guys earlier this…

Original PDF of the order: https://public-inspection.federalregister.gov/2026-21447.pdf

Ref: release, PR Starting from v0.7.0, the default port for llama server is now 9931 (ggml). Those who did not explicitly set the port, expect breaking change…

I've been using AI extensively for ML research, and I've noticed a bottleneck: brainstorming research directions and generating smoke run implementations has…

System service that watches your card, swaps and loads whatever you want, whenever you want. Don’t have to swap anything manually, collisions avoided, VRAM…

Came across this today and haven't seen it discussed here yet. It's apparently a new type of model (called Maxwell) that sits under a running program and…

I've been building whatmodel.sh, an open source AI leaderboard, and wanted to see how a labs' own benchmark scores compare with independent testers. Using…

Setup Self-hosted homelab plus side projects, ~22 GitHub repos. I work with several AI agents: Claude, Codex, and a self-hosted agent (Hermes). Two problems…

An ultra-efficient open-weight model for everyday work.

Meet the LiteRT Tensor API: giving developers native C++ control over the model graph to unify end-to-end ML computations on heterogeneous edge hardware.

Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.

We’re giving developers, enterprises, scientists, and consumers access to Gemini 4 Argon, our latest frontier model.

Learn how OpenAI is improving ChatGPT across low-resource programming languages, with new evaluations for software engineering, SQLite, and COBOL migration.

Released prompt-to-voice for all API customers. Create a custom voice from a text description through the API or voice Playground, then reuse it in GPT-Live…

Added native Decisions integration in GPT-Live. Your app can act while your user is speaking or react to what Live says. Let Live call Decisions directly…

The decades-old mystery of the origins of one of the most popular cryptographic standards has been explained.