2026-10-20 AI 日报

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…

A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.

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…

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

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,…

A high-throughput and memory-efficient inference and serving engine for LLMs

⭐️⭐️⭐️ Open-source, self-hosted alternative to Linear and Plane. Project management and issue tracking where teams and AI agents work side by side to plan and…

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

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,600+…

Memory-native evolution requires making memory an intrinsic capability of foundation models, enabling them to continuously accumulate and utilize information.…

Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through…

Reconstructing human activity from egocentric video requires more than recovering individual 3D components: the observer's motion, surrounding geometry, and…

Human egocentric experience offers a rich foundation for learning how the world is organized and how it changes through interaction. Realizing this potential…

Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert…

We study language-conditioned local navigation, where a robot must navigate to a text-specified target visible in its initial observation and stop at the…

Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones. Using neural…

Matryoshka Representation Learning (MRL) is designed to support flexible representation sizes by jointly optimizing nested prefixes. While effective, this…

Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the…

Experience generated during deployment offers an opportunity for robots to improve policy reliability through learning from their own executions. However,…

Merci de recevoir ce patient pour un avis dermatologique. Traitement en cours: crème à l’hydrocortisone. Dr Martin, Clinique du Parc. It says, "Merci de…

Over the past year, we’ve published lots of data that shows that frontier AI models are more than capable of discovering and exploiting security…

Summary: As part of our work experimenting with how Claude can help accelerate drug discovery, we asked an internal research model to design minibinders…

🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency.…

JUST IN: Anthropic recorded a staggering $80,000,000,000.00 net loss in the first half of 2026.

This is crazy good for studying to improve existing custom engines by community like gufo, halogen, strixite, Strata... by learning their secret sauces.

Gemini 4 Argon built a 3D periodic table synced to Tom Lehrer’s song, “The Elements.” Created in @Antigravity, it animates orbiting electrons, atomic data,…

We found DeepSeek V4.1 Flash 1017 beats GPT 6 Sol on our multi-step offensive cybersecurity task. Sol was tested via the Daybreak trusted access program. We…

Insane numbers, so far only Qwen3.8-27B is supported but wow those are some good numbers. Will watch closely when this lands in llama.cpp/vLLM ### Qwen 3.8…

https://x.com/deepseek_ai/status/2112476496283775135 https://github.com/deepseek-ai/deepseek-recipe…

Hey everyone! I'm working on an object-detection project and fine-tuning Meta's DETR model on a custom dataset of around 500 images. The main challenge I'm…

Very good so far. Must be the first time I actually believe the score. It's far from perfect, but it's extremely uncensored out of the box and fast. I haven't…

China just ordered 3mil RTX 5500 Pro for $11.4k a pop. Probably for llm inference and AI video gen. I suppose this card is now out of reach for local llm.

See how OpenAI, PerturbAI, and Scripps Research used distributed AI agents to uncover promising research leads in data from millions of brain cells.

Voxtral 3: Mistral's voice agent SDK for real-time speech in 50+ languages — accurate transcription, emotional TTS, deep tool use. EU-hosted or self-deployed.

You can now choose 12-hour prompt caching in the API. 12-hour prompt caching keeps shared instructions, tools, and context cached longer to benefit from lower…

Locked chats let you keep selected conversations in your account while hiding them from regular chat history, pinned chats, and search. Open them with your…

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