AI Lab

How do you forecast a month that has not happened yet? An introduction to time series, built on a simple regression you can run yourself, and an honest look at where it fails.

Picture yourself uploading a 50-page annual report, with two columns of text and a stack of financial tables, to a chatbot and asking one question: what was last year's revenue? In the bad case, the model makes up a number or insists the document never says. The

Phi-3 Mini runs on a laptop and beats models twice its size on Microsoft's own table. Why model size stopped being the first question.

The OWASP list for LLM applications, read from a finance desk: prompt injection, training-data leakage, and a supply chain of someone else's code.

A language model puts a probability on every possible next word, picks one, and runs the calculation again. Everything else follows from that loop.