Yesterday afternoon, OpenAI teased Sora, a video-generation model that promises to convert written text prompts into highly realistic videos. Footage released by the company depicts such examples as "a Shiba Inu dog wearing a beret and black turtleneck" and "in an ornate, historical hall, a massive tidal wave peaks and begins to crash." The excitement from the press has been reminiscent of the buzz surrounding the image creator DALL-E or ChatGPT in 2022: Sora is described as "eye-popping," "world-changing," and "breathtaking, yet terrifying." The imagery is genuinely impressive. At a glance, one example of an animated "fluffy monster" looks better than Shrek; an "extreme close up" of a woman's eye, complete with a reflection of the scene in front of her, is startlingly lifelike.

For the same reason that star players make bad coaches, models that make complicated decisions at high levels of abstraction come at a price, they can't easily explain their reasoning. This is a direct (and sometimes expensive) tradeoff. There is a similar paradigm for machine learning. The more powerful the model, the harder it is to interpret its inner workings. Sure, you may get a more accurate answer from a neural network, but how it arrived at that answer may be a total mystery. This can be a problem when trying to figure out what went wrong or how to improve it.