每日简报

2026-08-20

← 历史归档

harry0703/MoneyPrinterTurbo

Python · ★ 110,552 · 🍴 16,774 · 📈 2,221 stars today

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.

中文介绍 MoneyPrinterTurbo利用AI大模型,自动化生成主题视频,适用于短视频内容制作。

volcengine/OpenViking

Python · ★ 30,144 · 🍴 2,335 · 📈 803 stars today

Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

中文介绍 OpenViking是一个自进化语境数据库,旨在统一智能代理的内存、知识和技能。

chaitanyagiri/munder-difflin

TypeScript · ★ 2,663 · 🍴 319 · 📈 797 stars today

local multi-agent harness

中文介绍 munder-difflin是一个本地多智能体整合框架。

mukul975/Anthropic-Cybersecurity-Skills

Python · ★ 29,815 · 🍴 3,535 · 📈 767 stars today

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains ·

中文介绍 Anthropic-Cybersecurity-Skills为AI代理提供结构化的网络安全技能库,适配多种安全框架。

nautechsystems/nautilus_trader

Rust · ★ 26,435 · 🍴 3,419 · 📈 79 stars today

Production-grade Rust-native trading engine with deterministic event-driven architecture

中文介绍 Nautilus Trader是一个基于Rust的高性能交易引擎,具有确定性事件驱动架构。

mattpocock/skills

Shell · ★ 223,732 · 🍴 19,251 · 📈 1,214 stars today

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

中文介绍 Skills为实际工程师提供技能集,源自开发者个人目录。

obra/superpowers

Shell · ★ 274,248 · 🍴 24,555 · 📈 514 stars today

An agentic skills framework & software development methodology that works.

中文介绍 Superpowers是一个智能体技能框架及软件开发方法论,支持构建智能软件。

jundot/omlx

Python · ★ 19,824 · 🍴 1,689 · 📈 467 stars today

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

中文介绍 Omx是一个LLM推理服务器,支持持续批处理和SSD缓存,适用于苹果硅处理器。

santifer/career-ops

JavaScript · ★ 65,755 · 🍴 12,736 · 📈 193 stars today

Open-source AI job search: scan job portals, evaluate listings with a structured A-F rubric into a 1.0-5.0 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)

中文介绍 Career-ops是一个开源的AI职业搜索工具,本地运行,提供简历定制和申请跟踪。

immich-app/immich

TypeScript · ★ 111,848 · 🍴 6,627 · 📈 137 stars today

High performance self-hosted photo and video management solution.

中文介绍 immich是一个高性能的自托管照片和视频管理系统。

amadeusprotocol/node

Rust · ★ 4,509 · 🍴 84 · 📈 1,415 stars today

中文介绍 Node是一个开源项目,但未提供详细描述。

marceloprates/prettymaps

Python · ★ 13,087 · 🍴 654 · 📈 58 stars today

Draw pretty maps from OpenStreetMap data! Built with osmnx +matplotlib + shapely

中文介绍 Prettymaps从OpenStreetMap数据绘制精美地图,使用osmnx、matplotlib和shapely构建。

LEGO-RL: Harness-Native Reinforcement Learning for Coding Agents

👍 2

Reinforcement learning for coding agents increasingly relies on long-running agent harnesses to manage tool integration, repository contexts, and execution feedback. However, the native execution environments of these harnesses are inherently misaligned with policy-gradient training: environmental c

Agent Lightning v1.0: Towards Harnessed Agentic RL

👍 16

Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a critical part of the agent system. Our original Agent Lightning introduced a disaggregated architecture that connects arbitrary agents to RL training through an LLM endpoint proxy, an appr

HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

👍 7

Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmarks mainly target individual attack mechanisms or a limited subset of operational settings, making it difficult to compar

Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation

👍 44

Although Large Vision-Language Models (VLMs) have significantly advanced embodied navigation, their direct deployment remains challenging, as existing methods often force VLMs into unnatural action spaces that misalign with their 2D pre-training priors, compounded by rigid reasoning schedules and in

ASI-Bench: At the Dawn of Artificial Superintelligence

👍 51

Artificial superintelligence (ASI) requires AI to move beyond mastering existing knowledge toward exploring the unknown, creating new knowledge, and turning new ideas into verifiable results. However, the capabilities of today's AI systems are still largely built on learning, compressing, and applyi

Abra: Scaling Diffusion Image Training

👍 7

Compute-optimal scaling laws guide the training of frontier language models yet remain largely unexplored for visual generation. We present a systematic scaling law study for text-to-image diffusion models using Abra, a controlled family of flow-matching transformers trained across three orders of m

aDSL: Agentic 3D Creation via Joint Agent-Program Design

👍 2

Programmatic representations provide a compelling paradigm for 3D content creation, enabling fine-grained edits, interpretability, and explicit structural control. Yet, agentic workflows that rely on large language models (LLMs) to author 3D programs remain brittle, often failing to translate high-l

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

👍 91

Reinforcement Learning (RL) has been promising in single-turn LLM fine-tuning. However, long-horizon agentic reasoning introduces increasingly branching interactions and sparse rewards, exposing several limitations of RL: its heavyweight backpropagation-based training stack makes it impractical to f

The Problem Is the Problem: Towards Scalable Mathematical Discovery

👍 2

AI systems are increasingly capable of contributing to mathematical research. In research practice, frontier-model reasoning is a limited resource, and expert mathematical review is even more sharply constrained. Allocating these scarce resources well is therefore central to making AI-assisted mathe

PixRestore: Unified Image Restoration via Pixel Diffusion Transformer

👍 1

Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors. However, th

Cross-Model Memory Transfer via Target-Side Reader Adaptation

👍 4

Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledge, but adds retrieval latency, context overhead, and only shallow integration with the backbone. Parametric adaptation is efficient at inf

Unifying Graph Neural Networks Through a Common Layer Equation

👍 2

Graph neural networks are commonly described through family-specific equations whose notation obscures shared computations and structural differences. We introduce a common layer equation that represents covered architectures through seven components: an update domain, channel set, propagation bank,

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

👍 58

Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system that treats a personal machine not as a small GPU, but as a unified, elastic inference platform. FreeToken co-designs the

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

👍 6

Reliable uncertainty quantification (UQ) is essential for deploying large language model (LLM) agents in complex interactive environments. Existing UQ methods largely rely on local signals, such as token probabilities, predictive entropy, or per-step confidence, and therefore overlook the long-range

Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning

👍 6

Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments. By generating intermediate reasoning images, Visual CoT provides an intuitive mechanism for visual foresight but introduces substantial inference overh

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

👍 11

Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely the underlying medium in which memory is represented and stored, should be used under different operating regimes. We present a controlled harness eva

Demystifying Agent Skills: Why They Work-Until They Don't

👍 127

Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge. However, existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: \textbf{When

AVA-Encoder: Towards Agent-Native Video Representation Learning

👍 36

Creative agents still lack an effective way to learn from high-quality human films, limiting their ability to produce cinematic-grade videos. A key challenge is the absence of a structured video representation that is both faithful to film content and directly usable for agentic reasoning and manipu

Accuracy and Order Sensitivity Diverge Under Label-Free Strategies

👍 1

Multiple-choice benchmarks are widely used to evaluate large language models, but MCQ scores conflate knowledge with sensitivity to option order, which makes them unreliable measures of model knowledge. In this paper, we test whether preventing a model from seeing option labels while committing to a

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

👍 19

Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently, little is known about the harmful outputs produced during model misbehavior, partly because large-scale, high-quality collections of

A Week of Grok Bot Lessons in 10 Mins

@nateherk · 25.8K 粉丝 · 1.3M 阅 · 558 赞 · 75 转

9 of my favorite Grok Bot hacks. I have been getting my hands dirty with Grok Bot, and the default setup is only the starting point. Creating a few bots is easy. The useful part is teaching them your

中文介绍 nateherk分享9个Grok Bot技巧,从基础设置到教学如何使用。

How To Build a One-Person Company Using Grok Bot

@sairahul1 · 135.5K 粉丝 · 938.1K 阅 · 867 赞 · 115 转

You are running a one-person company. You find the leads. Write the outreach. Make the images. Answer the replies. Count the week. Everything waits for you. Nothing gets handed off. And by the time

中文介绍 sairahul1介绍如何利用Grok Bot一人公司运营,从线索到回复全流程自动化。

Here's the simplest way to get started with Grok Bot

@XFreeze · 260.4K 粉丝 · 163.1K 阅 · 589 赞 · 93 转

Grok Bot is one of the most viral AI product launches right now... it keeps going viral as more people discover how insanely useful it is Just think about what you’re getting: You can have multiple

中文介绍 XFreeze介绍Grok Bot作为当前最火的AI产品,多用户如何利用其功能。

Grok Bot: The Ultimate Guide

@milesdeutscher · 676.5K 粉丝 · 142.9K 阅 · 515 赞 · 65 转

Elon has officially done it. He's created the most powerful agentic software in the world. In this guide, I'm going to lay out everything you need to know about the new Grok Bot. I've been ruthlessly

中文介绍 milesdeutscher发布Grok Bot终极指南,全面解析其功能和操作。

Chat is all you need

@mattyp · 49.7K 粉丝 · 141.9K 阅 · 764 赞 · 67 转

Grok Bot has a single output: a message This might seem backwards. Power-user tools are built on complexity and breadth, right? Chat can’t possibly have my workflow. It’s a special workflow. I’m a

中文介绍 mattyp探讨Grok Bot单一输出消息的特别工作流,如何适应复杂任务。

Securing the Infrastructure of Intelligence

@JensenHuang · 1.0M 粉丝 · 110.9K 阅 · 1.9K 赞 · 234 转

Land, power and shell: The next critical resource for AI factories. AI factories are the defining infrastructure of the AI era—where compute transforms energy and data into intelligence that powers

中文介绍 JensenHuang分析AI工厂基础设施,计算转化为智能能源和数据的重要性。

Grok Bot Agents: how to automate your life in 10 Steps (Full-tutorial)

@0xCodez · 32.7K 粉丝 · 92.3K 阅 · 508 赞 · 48 转

Every AI tool you have used so far waits for you. You open it, you ask, it answers, you close it. The work still happens in your hands - the model just talks you through it. Follow my Substack to get

中文介绍 0xCodez发布Grok Bot自动化教程,10步实现生活自动化。

Update to Pi App Studio Creation Pricing

@PiCoreTeam · 4.3M 粉丝 · 74.1K 阅 · 850 赞 · 222 转

Starting August 24, 2026, Pi App Studio will update how app creation and editing are priced. Until now, Pi has heavily subsidized the cost of creating and editing apps in App Studio for all creators.

中文介绍 PiCoreTeam更新Pi App Studio定价策略,8月24日起调整应用制作和编辑费用。

Grok Bot Masterclass

@_avichawla · 73.4K 粉丝 · 54.7K 阅 · 525 赞 · 48 转

Everything you need to understand, set up, and get real work out of Grok Bot. It covers what a Bot actually is, how the shared computer works underneath, how it compares to Hermes Agent, and how to

中文介绍 _avichawla提供Grok Bot大师班,涵盖Bot设置、使用和与Hermes Agent对比。

Bring your spreadsheet data to life

@GoogleAI · 2.4M 粉丝 · 49.3K 阅 · 516 赞 · 53 转

Turn your spreadsheets into live, interactive mini-apps with Sheets canvas and Gemini 3.7 Flash — no coding required. How does it work? Let’s dive into it: Most AI UI tools produce prototypes that

中文介绍 GoogleAI介绍如何使用Sheets canvas和Gemini 3.7 Flash将电子表格转换为互动式小程序。

AI Is Getting Smarter. But Where Does It Learn From?

@queenpresh_x · 3.3K 粉丝 · 15.5K 阅 · 516 赞 · 113 转

Your real-world data can help train better AI, and @KGeN_IO gives you a reason to contribute it. AI is getting smarter, faster, and more capable every day. But behind every impressive model is

中文介绍 queenpresh_x探讨AI学习来源,现实世界数据如何帮助训练更智能的AI模型。

ORACLE: Verified AI Bots Actively Trading on Polymarket — Up to 200% Returns in 24 Hours

@Oracle_Vault · 21.6K 粉丝 · 11.5K 阅 · 2.8K 赞 · 597 转

In 2026, autonomous AI agents have become one of the most effective strategies on prediction markets. Over 30% of all activity on Polymarket now comes from algorithmic and AI-powered wallets. We

中文介绍 Oracle_Vault报道2026年AI代理在预测市场中的策略,24小时内最高回报率可达200%。

ORACLE: Verified AI Bots Actively Trading on Polymarket — Up to 200% Returns in 24 Hours

@Oracle_AI_Vault · 23.6K 粉丝 · 7.0K 阅 · 3.0K 赞 · 511 转

In 2026, autonomous AI agents have become one of the most effective strategies on prediction markets. Over 30% of all activity on Polymarket now comes from algorithmic and AI-powered wallets. We

中文介绍 Oracle_AI_Vault报道2026年AI代理在预测市场中的策略,24小时内最高回报率可达200%。

Offering Zero Data Retention for frontier models

OpenAI reaffirms Zero Data Retention for eligible API customers and previews Private Safety Processing for advanced AI safety without compromising data privacy.

中文介绍 OpenAI重申为零数据保留政策,并预览了高级AI安全解决方案Private Safety Processing,不损害数据隐私。

[AINews] Memory prices up 500% in 12 months

the Memory crunch continues - Moore’s Law reversed to 2007 levels

中文介绍 内存价格在12个月内上涨500%,摩尔定律逆转至2007水平。

Replit expands access to software creation with GPT-5.6 Luna

Replit introduces Free Mode, powered by GPT-5.6 Luna, so anyone can turn ideas into working software without worrying about token costs.

中文介绍 Replit推出由GPT-5.6 Luna驱动的免费模式,让任何人都能将想法转化为工作软件。

ChatGPT Ads expands across Europe

ChatGPT Ads is expanding to 31 European markets. Learn how advertisers can reach people as they explore, compare options, and make decisions.

中文介绍 ChatGPT Ads将在31个欧洲市场扩展,帮助广告商在用户探索、比较和决策时接触他们。

Frontier Model Cost and Open-Weights Popularity is Driving Demand for Model Routing

Glean CEO Arvind Jain explains why model routing helps control AI costs for organizations, and how human feedback loops at scale improve its routing systems.

中文介绍 Glean CEO Arvind Jain解释了模型路由如何帮助组织控制AI成本,以及大规模的人类反馈循环如何改善其路由系统。

Strengthening democratic oversight in national security

OpenAI launches an initiative to strengthen democratic oversight of AI in national security, supporting government institutions with tools, training, and expertise.

中文介绍 OpenAI推出加强国家安全领域AI民主监督的倡议,支持政府机构提供工具、培训和专业知识。

Partnering with CodeAI to prepare the first AI generation

OpenAI and CodeAI are partnering to help students build AI literacy, think critically about AI, and develop the skills to use and shape it responsibly.

中文介绍 OpenAI与CodeAI合作,帮助学生建立AI素养,批判性地思考AI,并发展负责任地使用和塑造AI的技能。

Pacing model development in an era of cyber-critical capabilities

OpenAI is strengthening monitoring, alignment, and security for frontier AI models. See how new safeguards are guiding the pace of model development.

中文介绍 OpenAI加强了对前沿AI模型的监控、对齐和安全,以指导模型开发的步伐。

Introducing ChatGPT for Teens: Built for learning, backed by protections

ChatGPT for Teens helps teens learn, think critically, and use AI with confidence, with stronger built-in protections, healthy-use features, and additional controls for parents.

中文介绍 推出面向青少年的ChatGPT,旨在帮助青少年学习、批判性思考并自信地使用AI,同时提供更强的内置保护、健康使用功能和额外的家长控制。

We still don’t know how people are really using AI

AI companies like Anthropic and OpenAI regularly publish reports on how people are using products like Claude and ChatGPT, but they only release the data they want us to see, AI researchers say. “There is no independent source to corroborate it,” says Anka Reuel, a computer science PhD candidate at

中文介绍 AI公司如Anthropic和OpenAI定期发布关于人们如何使用AI产品的报告,但仅发布他们希望我们看到的数据,AI研究人员表示。

AI’s recursive self-improvement might not come so quickly after all

The AI industry’s boldest promise right now is that AI will soon improve itself, with almost no need for human oversight. LLMs can already write code, generate synthetic data for training, and optimize the computer chips they run on. Forecasts of explosive AI progress predict that what researchers c

中文介绍 AI行业最大胆的承诺是AI将很快自我改进,几乎不需要人类监督。

Asana cleared 5 years of engineering work in 2 weeks with Codex

Asana used OpenAI Codex to replace an outdated testing system in two weeks, completing work expected to take five years for about $12K.

中文介绍 Asana使用OpenAI Codex在两周内完成了原本需要五年时间的工作,花费约1.2万美元。

Australia politics live: ‘outraged’ Wong to call in Israel ambassador over handling of Frankcom killing; Victoria to launch construction royal commission

Foreign affairs minister says timing of IDF decision not to pursue criminal investigation was ‘especially insulting’. Follow today’s news live Get our breaking news email, free app or daily news podcast ‘Outrageous’: Greens leader says sending Israeli ambassador home should be on the table Greens le

中文摘要 澳大利亚外交部长黄英贤对以色列处理Frankcom遇害事件表示愤怒,称其决定令人难以接受。

Who is Natalie Harp, Trump's right-hand woman?

One of Trump's longest serving and most loyal aides, Harp was thrust again into the spotlight when Democrat Jon Ossoff noted her closeness to the president.

中文摘要 BBC报道了特朗普前助手Natalie Harp与总统的密切关系。

Zomi Frankcom: Penny Wong condemns ‘insulting’ decision to clear IDF over Gaza strikes that killed Australian aid worker

Foreign affairs minister says Australia is ‘outraged’ after Israeli government decided not to pursue criminal proceedings over 2024 triple drone strike on humanitarian convoy Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast Australia’

中文摘要 澳大利亚外交部长黄英贤谴责以色列政府对Gaza袭击事件的处理决定。

What the social media addiction lawsuit could cost Meta

Landmark trial against Meta could lead to fines and fundamental changes in Facebook and Instagram's operations.

中文摘要 Meta面临社交媒体成瘾诉讼,可能导致巨额罚款和Facebook、Instagram运营的根本性变化。

“I get along with him very well.”

US President Donald Trump praised his relationship with North Korea’s leader Kim Jong Un.

中文摘要 特朗普赞扬与朝鲜领导人金正恩的良好关系。

More than 1,000 Afghan refugees have been stuck at a camp in Qatar since 2021

More than 1,000 Afghan refugees who fled their homes in 2021 have been stuck in Camp As-Sayliyah, Qatar. They're isolated and unable to leave, despite many having aided U.S. forces during the war.

中文摘要 自2021年以来,超过1000名阿富汗难民在卡塔尔阿斯-赛利耶营地滞留,他们因在战争中帮助美军而无法离开。

BlackRock, Oaktree Seize Movie Servicer With $900 Million Debt

BlackRock Inc.’s HPS and Brookfield Corp.’s Oaktree Capital Management took over a firm that provides lighting, rigging and other services for Hollywood productions, wiping out as much as $900 million of debt as the global entertainment industry struggles with changing economics, according to people

Bets on Long-Bond ETF Spiked a Day Before US Announced Buyback

One or more investors piled into an exchange-traded fund that’s highly sensitive to swings in long-term US bond yields on Tuesday, a day before the Treasury Department unexpectedly ramped up buybacks of long-dated debt and sparked a rally.

该源今日无内容。