每日科技速递 - 2026-06-05
每日科技速递 - 2026-06-05
本日焦点:asgeirtj/system_prompts_leaks: Extracted system prompts from Anthro... (15pts) | rohitg00/ai-engineering-from-scratch: Learn it. Build it. Ship it f... (15pts) | lsdefine/GenericAgent: Self-evolving agent: grows skill tree from 3... (14pts) | Coinbase launches pre-IPO perpetual futures, starting with SpaceX (12.0pts) | CherryHQ/cherry-studio: AI productivity studio with smart chat, aut... (11pts)
🧠 LLM / 大模型
• 🔥8 | sgl-project/sglang: SGLang is a high-performance serving framework for large language models and multimodal models. — SGLang is a high-performance serving framework for large language models and multimodal models. https://github.com/sgl-project/sglang
• 🔥8 | yamadashy/repomix: 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like C — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) o... https://github.com/yamadashy/repomix
• 🔥7.0 | How Endava is redesigning software delivery around AI agents — https://openai.com/index/endava-frontiers
• 🔥7.0 | Dreaming: Better memory for a more helpful ChatGPT — https://openai.com/index/chatgpt-memory-dreaming
• 🔥7.0 | Biodefense in the Intelligence Age — https://openai.com/index/biodefense-in-the-intelligence-age
🤖 AI Agent
• 🔥14 | lsdefine/GenericAgent: Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption — Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption https://github.com/lsdefine/GenericAgent