Probably because taxi companies are a dime-a-dozen across various cities and states, and the capital required for an engineering investment to pull something like this off just isn't there at any given shop. It's a technology problem that the existing industry faces, and because the existing competition is essentially a coalition of independent companies, they can't band together to build something like this without a joined effort (nigh impossible).

I was recently in Pittsburgh and saw a clunky touch-screen app stuck to the back of the passenger seat that sounded just like Uber, so it's clear that someone out there is working on building Uber-like dependability for your taxi. But I also remember talking to the cab-driver on that trip, and having him tell me that their 'dispatch' is still one person sitting in an office somewhere manually dialing and dispatching cabs to received calls. The status quo in the industry is just so ancient in so many ways. Here's to hoping they can start moving and respond though.