Prompt Engineering
8 articles tagged with this topic
Two Years On, AI Coding Still Has 4 Pitfalls — Bottleneck Was Never the Model
A Juejin roundup lists AI coding's 4 most common pitfalls. Two years on, code comes out faster — but judging whether it's correct still has no shortcu
AI Long-Form Writing Gets Formulaic — A Developer's 'Planned Derailment' Fix
A developer fixed AI long-form writing's self-copying habit at chapter 20 with 8 triggers + 6 disruption actions. Implications stretch beyond web fict
Industrial LLMs Find a New Trick: Let AI Grade Its Own Homework — Academia Starts Taking "Peer
A quiet trend heating up in early 2026: borrowing academic peer review for industrial LLMs — letting models review and revise each other. Cheaper than
AWS Agent Auto-Tuning: Blind Bug Guessing Ends as AI Degrades Post-Launch
AWS AgentCore auto-tunes AI Agents via production data and A/B tests. Focus shifts from building to maintaining agents, ending post-launch degradation
LangChain Templates Take Over Prompts: AI Apps Exit Artisan Era
LangChain's prompt templates solve hardcoding chaos. AI dev shifts from ad-hoc crafting to version-controlled engineering—a key step for enterprise AI
Examples Beat Instructions for LLMs: Why Few-Shot Prompts Stabilize Output
Zero-shot vs. few-shot prompting determines AI output stability and dev costs. Using the right demonstration method drastically reduces ineffective AI
AWS Launches LLM Migration Framework: 2-Week Model Swaps End Vendor Lock-in
AWS LLM migration framework enables 2-14 day model swaps. Enterprise AI shifts to on-demand switching, cutting lock-in, but auto-evals risk losing nua
AI Skills: Reusable Task Units for Agent-Based Workflows
AI Skills are modular, reusable prompt-and-tool packages for AI agents, structured like npm packages for teams.