2026年8月30日 技术热点总结

项目简介：ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.

技术栈：TypeScript、ai-agents、chatgpt、codex、mcp、model-context-protocol、oauth

核心介绍：> ChatGPT thinks. Codex works. > ChatGPT 负责思考，Codex 负责干活。 API 额度做规划和 Review。本项目把”思考”交给你已付费的网页版 ChatGPT， Codex 只负责执行。不用 API Key、不搞逆向代理——官方网页 + 只读 MCP 桥接。 scarce API/Codex tokens on planning and review. This project moves the thinking to the subscription you already pay for; Codex only executes. No API keys, no reverse proxy — official web UI plus a read-only MCP bridge. 完全保留在 Codex 手里。你的仓库永远不会被上传：ChatGP…

项目简介：🌐 🔌 The MetaMask desktop app enables browsing Ethereum blockchain enabled websites

技术栈：CSS、bitcoin、bitcoin-wallet、crypto、cryptocoins、cryptocompare-api、cryptocurrency、dapp、ethereum

核心介绍：MetaMask Desktop is a cross-platform desktop application for managing a cryptocurrency wallet, interacting with Web3 applications, and accessing decentralized ecosystems such as DeFi and NFTs. The project provides a desktop-first alternative to the browser extension experience, offering improved stability, performance, and system-level integration for Windows, macOS, and Linux users. This p…

项目简介：De-AI writing skill for Claude Code, Codex, Grok Build, and Antigravity — narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).

技术栈：agent-skills、ai-writing、antigravity、claude-code、codex、developer-tools、fiction、grok

核心介绍：> De-AI writing at the layer that actually gives AI away. Fiction gets its narrative architecture repaired before anyone touches word choice; professional documents (release notes, PR replies, postmortems, tickets, technical articles) each get rules matched to their venue.

项目数据：⭐…

技术栈：Python

核心介绍：本仓库保存《数理化自学丛书》17 册的原始扫描 PDF、语义化 Markdown、扫描插图资源和可复现 EPUB3 构建工具。 本项目计算资源由 交易猫实验室（TradeCat Labs） 赞助。 作者元数据统一为“数理化自学丛书编委会”，电子书语言统一为 zh-CN。 Markdown 与 books/assets/ 保持在同一源文件区，因此正文中的 assets/… 相对引用可直接解析；仓库根目录不放置单册电子书源文件。 原始 PDF 深度审计额外需要 PyPDF2 3.x、qpdf、Poppler（pdfinfo、pdfdetach、pdfsig、pdftotext）和 ExifTool。 完整审计并构建： 仅审计源文件： 审计17份原始扫描 PDF 的哈希、结构、附件、主动内容和隐私元数据： python3 scripts/build_epubs.py –book ‘代数（第一册）’

项目数据：⭐ 604 Stars，🍴 120 Forks

High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representation should include physically based rendering (PBR) modalities such as albedo, metallic-roughness, and surface normals. We propose Luce, a 3D representation that unifies geometry and PBR materials within a voxelized multimodal Gaussian cloud, using dedicated Gaussian primitives for each modality. A variational autoencoder compresses this representation into a unified material-aware latent space. …

Recent advances in inference-time scaling have significantly improved the reasoning performance of large language models (LLMs). However, these methods typically rely on repeated generation or external verification. To address this limitation, we introduce CritICL, a novel inference-time framework that improves reasoning while maintaining high efficiency. Our key insight is that LLM failure modes exhibit structured patterns across model scales within the same family. Instead of treating failures as undesirable outputs, CritICL leverages them as a source of guidance. Specifically, we utilize…

Contact-rich manipulation requires adapting to contact states that can evolve substantially within an action horizon. However, chunk-based vision-language-action models predict complete action chunks from observations collected before execution, leaving tactile conditioning stale during execution. Existing tactile-reactive approaches typically rely on separate high-frequency controllers, which increase both architectural and training complexity. In this paper, we introduce TacForcing, a streaming action-generation framework that effectively incorporates execution-time tactile feedback. Inst…

Evaluation artifacts specify a forward computation: a task, scorer, and reported metric. They do not necessarily license the claim attached to that metric because the historical evidence and alternative semantics needed to replay it may be unbound. We formalize this missing claim-replay layer through a frozen substrate D, a grounded family F, a claim query q, and the resulting identified set. We then census all 124 mechanically eligible Inspect Evals units at a pinned commit. Every unit receives a terminal disposition; 110 stop before deterministic inference because required historical evid…

Conventional video editing primarily focuses on scene-level content, whereas live streaming places greater emphasis on the human subject. However, directly applying existing video-editing methods to human-centric live streaming remains challenging, as they may introduce facial-expression inconsistencies and typically depend on multiple offline inference steps, making them unsuitable for real-time interaction. We propose EditaLive, a novel framework for real-time streaming character video editing. In detail, we start from a pretrained image animation model (Wan-Animate), which naturally deco…

Long-horizon agent runs generate experience that can improve both the current run and future work. Most self-improvement methods process this experience only after execution ends, so they cannot redirect the active run or immediately apply and validate lessons learned from it. We argue that self-improvement should instead be live, using emerging experience both to redirect the active run and to update the persistent harness. Existing agent architectures do not fully support this goal. Single-agent self-correction combines task execution and trajectory assessment within one context, while su…