🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

看到Anthorpic怎么在组织内部使用claude code，我觉得大部分文本产出类的工作都危险了… www-cdn.anthropic.com/58284b19e702b4…

So, what exactly is an "agent"? I've spent a ton of time trying to define this because nobody seems to be on the same page. Anthropic's definition is my favorite one by far. We have 3 different concepts: 1. Agentic systems 2. Agentic workflows 3. Agents Let's define them one

Claude Code as orchestrator agent Subagent + /command to make loop iterations

Introducing GLM-4.5 and GLM-4.5 Air: new flagship models designed to unify frontier reasoning, coding, and agentic capabilities. GLM-4.5: 355B total / 32B active parameters GLM-4.5-Air: 106B total / 12B active parameters API Pricing (per 1M tokens): GLM-4.5: $0.6 Input / $2.2

Less than 89 hours ago, Claude Code unlocked sub agents. Minds are blown. And people are already building with their own agentic AI dev team. 10 wild examples:

非常棒的讨论。必须要mark。 agent和workflow并不互斥，可以并存，我倾向于是嵌套的关系，agent>workflow，确定性的、经常重复的过程可以固化下来成为workflow，为agent解决问题所用。 我觉得随着llm的生成能力的提升，完全可以由agent来生成workflow。类似flowreasoner的方向。

卷起来，看来趁着硅谷奔着超级智能，这下大模型token市场被中国开源LLM卷沸腾起来了！

江浙沪包邮区台风🌀？

和LLM这类认知智能系统交互，与其他的系统都不太一样的地方是：meta interaction 可能源自这类系统的meta learning特性。 就是你可以一直回溯，只到能继续这种交互。 从最早的prompt，如果你不知道提问，你可以问LLM怎么写提示词；今天的vibe coding也一样，你可以一直回溯到你怎么敲下claude

𝙩𝙮≃𝙛{𝕩}^A𝕀²·ℙarad𝕚g𝕞 S Li