- Published on
RAG isn't about vector databases and embeddings, or any specific architecture. It's about retrieving relevant context well.
Llms
All Posts
- ai (8)
- agents (7)
- cybersecurity (4)
- open-source (4)
- context-engineering (3)
- prompt-engineering (3)
- mcp (3)
llms (3)
- windows (2)
- internals (2)
- passwords (2)
- post-exploitation (2)
- auth (2)
- oauth (2)
- prompting (2)
- malware (1)
- evasion (1)
- operating-systems (1)
- typescript (1)
- identicons (1)
- npm (1)
- bun (1)
- nextjs (1)
- search (1)
- retrieval (1)
- networking (1)
- cryptography (1)
- vllm (1)
- inference (1)
- rag (1)
- cryptopgraphy (1)
- saas (1)
- a2a (1)
- protocols (1)
- software-engineering (1)
- Published on
Exploring the syntactic and semantic differences between XML and JSON and why the former provides a more robust structure for complex LLM prompts- Published on
This is a transcription of a talk I gave at vLLM's office hours after landing vLLM's first-of-its-kind tool calling implementation that allows using OpenAI-compatible tools and tool streaming with opens-source models.