September 15, 2025 Why I Switched From Cursor to Claude Code After a year with Cursor, I moved to Claude Code's CLI. No IDE lock-in, better context management, and a workflow built around plans and persistent memory.
llmtoolingclaude-code
Read article
Conversational AI: From RAG Prototypes to Domain-Specific SupervisionDecember 12, 2024 The Hidden Cost of Embedding OpenAI's embedding API charges per token across ingestion, re-ingestion, and every query. Switching to a local Ollama model eliminated the recurring cost with comparable retrieval quality.
ragembeddingsllmollama
Read article
Conversational AI: From RAG Prototypes to Domain-Specific SupervisionNovember 28, 2024 Tool-Forced RAG: Stopping the LLM From Making Up Clinical Guidelines LLMs confidently generate plausible clinical advice that doesn't match published standards. Forcing document retrieval for professional questions prevents this.
ragllmsafety
Read article
Conversational AI: From RAG Prototypes to Domain-Specific SupervisionNovember 20, 2024 Per-Channel vs Per-User: What Memory Model Works for AI Chat Slack conversations are collaborative. Persisting context per channel captures the full picture. Per-user memory misses half the conversation.
llmarchitectureslack
Read article
Conversational AI: From RAG Prototypes to Domain-Specific SupervisionNovember 12, 2024 Rewriting a Chat API in Go for Lambda: Cold Starts and Trade-offs The Node.js chat API worked but Lambda cold starts were slow and memory usage was high. Go fixed both, but the rewrite taught me more than I expected.
goawsllm
Read article