Showing 37–45 of 48

Aug 26MODELSHow to read a model card critically6 min ↗Aug 20PAPERSPreference tuning: RLHF and DPO side by side6 min ↗Aug 14TESTSDoes "think step by step" help on short tasks?6 min ↗Aug 08AGENTSMemory for AI agents: what to store, what to forget6 min ↗Aug 05BENCHMARKSWhen a benchmark saturates, what should replace it?6 min ↗Jul 30MODELSDistillation explained for builders6 min ↗Jul 26PAPERSTokenizers: the layer everyone ignores until it bites6 min ↗Jul 22TESTSHow to red-team an LLM chatbot before your users do6 min ↗Jul 18PROMPTSWhy "don't do X" instructions fail, and what to write instead6 min ↗