What you give a small model
One small AI model scores a few points behind the best on short legal questions and far behind on a long tax research job. The tests cannot tell your firm which work to give it.
One small AI model scores a few points behind the best on short legal questions and far behind on a long tax research job. The tests cannot tell your firm which work to give it.
On a public chatbot the profession’s guidance points one way, and on a paid tool it is less clear. This article argues that a useful first question is what the client would expect.