Building LLM Powered Features (lightning talk)

Transcript

1. ⚡lightning talk ⚡ 
 Building LLM Powered Features " Radoslav Stankov
3. #
4. Radoslav Stankov @rstankov rstankov.com
5. https://tips.rstankov.com
7. 1.AGI 2.AI taking developers jobs 3.Vibe coding 4.How fast AI moving 5.Agents / MCP I'm not talk about
9. LLMs are already incredible, and there is years of work to be done to fully productize the capabilities that exist today.
15. MODEL GPU Network API
16. await fetch("https://api.openai.com/v1/chat/completions", { method: "POST", headers: { "Content-Type": "application/json", "Authorization": "Bearer YOUR_OPENAI_API_KEY" }, body: JSON.stringify({ model: "gpt-4", messages: [ { role: "system", content: "You are a helpful assistant." }, { role: "user", content: "Explain what LLM is" } ], temperature: 0.7 }) });
17. Instructions (system prompt)
18. Input (user prompt)
22. Evals