Small language models: your competitors are already training theirs
Rivals are moving routine AI work to small models they own, at about a tenth of the cost. Why SLMs win the enterprise and how to start before the gap compounds.
Tagged “data”
Everything Sunil Kumar has written about data in the context of agentic AI in production.
The evaluation set that measured the wrong thing
A document agent scored 94 percent on its evaluation set and failed in production. The set had been written by the team that built the agent.