Learn: LLM APIs and prompting

1. Prompt engineering overviewAnthropic · Where to start when a prompt doesn't do what you want.Mark done
2. Prompt engineeringOpenAI · Clear instructions, examples and a way to check the result.Mark done
3. Prompt design strategiesGoogle · The same craft, with Gemini's examples.Mark done
4. Structured model outputsOpenAI · Answers your code can read, every time.Mark done
5. Prompt cachingAnthropic · Paying less when every call starts the same way.Mark done
6. Effective context engineering for AI agentsAnthropic · Choosing what the model sees, beyond the prompt.Mark done

• LLM (large language model)
• Token
• Prompt
• System prompt
• Context window
• Chain of thought
• Prompt injection
• API

1. Multi-Target Few-Shot Prompting with Diffusion Language Models
2. SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

More in Language models →

1. mksglu/context-modeContext window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
2. ranxianglei/billion-contextA context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).上下文压缩插件，兼顾小窗口(100k上下文足矣)省token(省5倍token)和超长会话(数月级别几十亿token单会话)。billion-context is all you need

Everything rising this week →