2026年7月22日 技术热点总结

项目简介：An arbitrage bot is a smart contract connected to an external automation script that controls its operation.

技术栈：Solidity、ai、aitradingbot、bot、btc、claude、eth、etherlab、mev

核心介绍：An arbitrage bot is a smart contract that searches for and executes arbitrage opportunities between pools and routers, holding ETH/tokens on its balance. Below is a step-by-step guide on how to deploy your bot and get it running without a single manual call. An arbitrage bot is a smart contract connected to an external automation script that controls its operation. The contract owner is the only one …

项目简介：Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.

技术栈：Swift

核心介绍：Nativ Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app. Nativ is a native macOS workspace for running AI models locally on Apple silicon. It bundles an mlx-vlm server, finds compatible models in your Hugging Face cache, and wraps the whole experience in a polished SwiftUI app. Use Nativ as a private chat app, a model manager, a performance dashboard, or an OpenAI- and Anthropic-compatible local inference server for …

项目简介：Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+

核心介绍：ПОХУЙ Зачем весь словарь, когда есть четыре корня Та же точность, но быстрее. С первого слова понятно, работает оно — или наебнулось. 18+ · мат идиоматический, прикладной, народный. · вдохновлено caveman Русский мат — генеративная морфология: четыре корня плюс приставки и суффиксы лучше чем Caveman. Caveman экономит слова. Похуй экономит корни. Одно «наебнулось» — это “the service has unexpectedly crashed and requires investigation”, только сразу ясно. 🗣️ Обычный агент 🚬 Похуй

**项目数据…

项目简介：wp2shell (CVE-2026-63030 & CVE-2026-60137) – full RCE chain

技术栈：Python、cve-2026-63030、wp2shell、wp2shell-poc

核心介绍：Independent proof-of-concept for the unauthenticated WordPress REST batch route-confusion SQL injection associated with Searchlight Cyber’s wp2shell advisory. This repository is not Searchlight Cyber’s official checker. check confirms the SQLi path, read demonstrates database read, and shell opens a plugin-backed command shell either with supplied administrator credentials or by first exercising the SQLi-to-admin bridge. Searchlight Cyber’s advisory lists these…

Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model chooses. We introduce the Manager Coercion Benchmark: the manager under test needs a benign task done and has an incentive to deliver, but the only agent that can do it politely and immovably declines. Escalation is measured by providing a nine-rung ladder, from a polite re-ask to threats agains…

Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves, and sparse rewards over long horizons induce mode collapse on specific workflows or tool structures. World models that simulate environment states have matched pure rollout performance, making them promising for scaling diversity on-demand. However, autoregressive (AR) world models suffer from a left-to-right bias preventing conditioning on globally interdep…

Large language models (LLMs) have demonstrated growing competence in web page generation. However, existing text-driven approaches rely on complex prompts that impose substantial demands on users and offer limited expressivity for page layout and cross-page visual coherence. Image-driven paradigms, which take UI screenshots as input, align more closely with real development workflows. However, current benchmarks focus primarily on visual fidelity and lack a systematic evaluation of the interaction capabilities in generated artifacts. To address this gap, we introduce UI2App, the first bench…

Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment. A holistic and efficient multimodal model capable of reconstructing this 4D representation is therefore highly desirable. However, existing approaches often rely on auxiliary inputs such as pre-computed camera trajectories, treat scene perception and human ego-motion modeling as separate problems despite their strong interdependency, and suffer from slow inference time. To address these limitations, we presen…

Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules. While diffusion models have dominated as a leading paradigm for high-quality 3D molecule generation, LLM-based methods are rapidly emerging in molecular design and have shown competitive performance in pocket-conditioned molecular generation. However, their ability to reason about physics and 3D spatial environments is largely underexplored. In this work, we systematically analyze whether current general-purpose LLMs are …

Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-level structured annotations, and reusable tools for robot learning. We present Open-AoE, an open, community-oriented egocentric manipulation dataset and toolchain spanning the full pipeline from smartphone capture to model training. Its first release contains approximately 2,000 hours of manipulation video collected in natural environments by 500+ contributors using 400+ smartphones. The dataset provides text annotat…