After years of premature hype and unfulfilled promises in the field of autonomous vehicles, something has happened recently that surprisingly few people seem to have noticed: truly driverless cars have arrived.

Today, as a member of the general public, you can download the Cruise app (it looks just like the Uber or Lyft app) and hail a driverless vehicle—with no one behind the wheel—to take you from Point A to Point B on the streets of San Francisco.

Cruise currently only offers these driverless rides at night (between 10 pm and 5:30 am), but the company is poised to make the service available 24/7 throughout San Francisco. Expect this to happen within weeks. Cruise’s rival Waymo is close behind.

In 2023, robotaxi services will rapidly transition from a fascinating novelty to a viable, convenient—even mundane—way to get around the city. The number of robotaxis on the road and the number of people who use them will surge. In short, autonomous vehicles are about to enter their commercialization and scaling phase.

Rollout will happen on a city-by-city basis. Beyond San Francisco, expect fully driverless services to become available to the general public in at least two more U.S. cities next year. Plausible candidate locations include Phoenix, Austin, Las Vegas and Miami.

If you enjoyed this market, please check out the other 9! https://manifold.markets/group/forbes-2023-ai-predictions

This market is from Rob Toews' annual AI predictions at Forbes magazine. This market will resolve based on Rob's own self-assessed score for these predictions when he publishes his retrospective on them at the end of the year.

Since Rob resolved and graded his 2022 predictions before the end of 2022, I am setting the close date ahead of the end of the year, to (try to) avoid a situation where he posts the resolutions before the market closes. In the event that his resolution post falls in 2024, my apologies in advance. If he hasn't posted resolutions at all by February 1, 2024, I will do my best to resolve them personally, and set N/A for any questions that I can't determine with outside source data.

-----

Edit 2023-07-05: Last year Rob used "Right-ish" to grade some of his predictions. In cases of a similar "Right-ish" (or "Wrong-ish") answer this year, I will resolve to 75% PROB or 25% PROB, respectively. This will apply for similar language too ("mostly right", "partial credit", "in the right direction"). If he says something like "hard to say" or "some right, some wrong", or anything else that feels like a cop-out or 50% answer, I will just call that N/A.

Thanks to Henri Thunberg from this comment in requesting clarification!