Dev group chat: skip runtime LLM web search, index products via API instead
vxnuaj · x · 2026-10-15
A screenshot of a developer group chat debates search architecture for a product app: index items from the Sephora / Google Shopping API and embed them into a database rather than doing expensive, inaccurate runtime LLM web search — since inference costs more than SQL queries and web search is just an API call. The other side suggests fine-tuning an LLM or using cheap Qwen3.7 flash, with the poster threatening to mock them on Twitter.
More from coding & agent
- How Codex Happened: Inside OpenAI's coding comeback from a failed launch — every · 2026-10-16
- Claude counts tokens, not messages: 10 tricks to make your usage limit last all day — Aiden_Tech_Ai · 2026-10-16
- How to convert 20-year-tenure engineers to AI-native development before deciding who to retrain — alex_verem · 2026-10-16
- LangChain revamps human-in-the-loop middleware with typed schemas for tool interrupts — Hacubu · 2026-10-16
- Robot fully controlled by frontier LLMs assembles gadgets autonomously for 1.5 hours error-free — ihorbeaver · 2026-10-16
- Why the future of agents is basically Node and JavaScript, in one argument — verrsane · 2026-10-16