AI Glossary
What is Prompt engineering?
Prompt engineering is the practice of structuring instructions, examples, context, and output formats so a model performs a task consistently. Core techniques include role assignment, few-shot examples, chain-of-thought requests, and explicit output schemas. It is the cheapest capability lever — always try a better prompt before fine-tuning.
News momentum
Mentions in recent AI news titles and summaries, refreshed from the ingestion stream.
3
+1 vs prior 7d
- "RAG improves technical quality, in particular factual accuracy, and prompt engineering steers social representation as requested."
I've s…
bluesky-ai · 2h
- [Blogged] Prompt Engineering Is the Wrong Mental Model for AI Agents aarontay.substack.com/p/prompt-eng...
bluesky-ai · 16h
- Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
arxiv-ai · 5d
- Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation
arxiv-ai · 12d