Prompting vs RAG vs fine-tuning: how to choose
Does not know something means retrieval. Does not behave right means fine-tuning. Was not told properly means prompting, and that is most cases.
Read More
Ollama vs llama.cpp vs vLLM: which to run locally
Serving one person and serving two hundred are different engineering problems. The tool that wins at one loses badly at the other.
Read More
Flagship vs entry-tier AI models: when the cheap one is enough
The frontier model wins the comparison. The cheap model wins the invoice. Which matters depends entirely on your volume.
Read More
Tokenisation explained: why a model cannot count the letters in strawberry
Strawberry might be two tokens. The model is being asked to count letters inside symbols it cannot see inside.
Read More
How coding agents actually work, stage by stage
The model never touches your repository. It names a tool and supplies arguments, and your code decides whether to run it.
Read More
Enterprise AI keeps failing at deployment, not capability
A company paid $63 million because nobody could tell an agent what the job actually was. That is not a model problem.
Read More
Why AI labs publish open weights, and what it costs you
Give away the tier below your best, sell the product built on your best. That is not generosity. It is a funnel.
Read More
The three-week AI model release cycle is a cost, not a feature
A three-week release cycle means the model you validated against is a generation old before your evaluation finishes.
Read More
Every AI capability now spawns an industry to contain it
A technology that needs four industries to make it safe to use has not finished being built. It has finished being sold.
Read More
Skan, NewCore and Naive raise $164M for agent infrastructure
Four rounds, no model companies. All of them selling the scaffolding agents need before an enterprise will run them.
Read More
Cognition is reportedly raising at $40B, three months after $26B
Annualised run rate is one good month multiplied by twelve. That distinction matters most when growth is this fast.
Read More
CodeRabbit raises $143M because reviewing code got harder than writing it
Generation costs collapsed. Reading code is still done at human speed, by people who did not write it.
Read More