Showing 28–36 of 48

Sep 29TESTSStructured outputs vs. plain prompts: when constrained decoding is worth it6 min ↗Sep 28PROMPTSSystem prompt templates for production: six copy-ready examples6 min ↗Sep 25AGENTSStep budgets and stopping rules for AI agents6 min ↗Sep 21PROMPTSPrompting for citations that actually check out6 min ↗Sep 17MODELSSmall models, big jobs: where tiny models quietly win6 min ↗Sep 14PAPERSMixture of experts, without the hype6 min ↗Sep 08BENCHMARKSDesigning an LLM latency benchmark that matches what users feel6 min ↗Sep 03AGENTSHuman-in-the-loop patterns that don’t annoy the human6 min ↗Aug 30PROMPTSDecomposition prompts for long, messy tasks6 min ↗