-
Quantization in practice: running a capable model on one consumer GPU
Running a capable language model locally is mostly a memory-management problem.
-
Structured output and JSON mode without the model going off the rails
Modern LLM applications often fail at a surprisingly mundane boundary: the model says something intelligent, but your program cannot safely consume it.
-
Fine-tuning vs LoRA vs prompting: choosing the cheapest path that works
The cheapest model-customization strategy is not the one with the smallest training invoice. It is the one that reaches the required quality level with the lowest total lifecycle cost.
-
Context windows, KV-cache, and why long prompts get expensive
Modern large language models can accept remarkably long context windows. It’s tempting to assume that if a model supports 128K, 200K, or even 1M tokens, you should simply keep appending more informati
-
Tokenization pitfalls: why your LLM miscounts characters and money
If you’ve ever asked an LLM to count letters in a word, estimate API cost, or enforce a strict character limit, you’ve probably seen surprising results.
-
How transformer self-attention actually works, with a runnable toy
Transformers power modern large language models, image generators, coding assistants, and multimodal AI systems. The core idea behind them is surprisingly compact: self-attention lets every token deci