Showing 10–18 of 48

Nov 02TESTSLLM temperature explained: what actually changes from 0 to 1.57 min ↗Oct 31PROMPTSStructured output without JSON mode: 7 patterns that hold up6 min ↗Oct 29PAPERSSparse attention explained: sliding windows, global tokens and block sparsity6 min ↗Oct 28MODELSQuantization without tears: what you lose at 8, 4 and 3 bits6 min ↗Oct 26TESTSHow to run an 8B LLM on a laptop: hardware, quantization and tools6 min ↗Oct 24BENCHMARKSModel graders are useful, if you calibrate them first6 min ↗Oct 22BENCHMARKSLost in the middle: why long-context models still forget, and how to test it6 min ↗Oct 20TESTSRAG chunking strategies compared: fixed, recursive, structural, semantic and parent-child6 min ↗Oct 19MODELSAI-assisted coding that survives code review: a practical workflow6 min ↗