On Machine Intelligence

Syndikovat obsah On Machine Intelligence
Why Artificial Intelligence and Machine Learning are changing the world
Aktualizace: 17 min 15 sek zpět

Bad headlines distract from real AI problems

20 Srpen, 2018 - 23:09

For several years now, few articles about artificial intelligence in the popular press are published without being accompanied by a picture of a Terminator robot. The point is clear: artificial intelligence is coming and it is terrifying.

Having sown the seeds of fear, the headline writers are now subtly reinforcing that view.

Take TechCrunch, which claims on its Editorial page to be “delivering top-notch reporting on the business of the tech industry”. This week it covered a story about Google using machine learning algorithms developed by its sibling company, DeepMind, to improve the efficiency of it’s data centres. These algorithms will look after the cooling systems and should deliver energy savings of 30%. This is a really great use of AI, making an expensive process cheaper and being good for the environment too.

But the headline is pure click-bait. Instead of focusing on the positives, the headline reads “Google gives its AI the reins over its data center cooling systems”. It invokes mental images of Skynet, HAL 9000 and even VIKI from I, Robot taking over. Yes, Google has an AI. It’s giving more control to it every day. You should be frightened.

Except it’s not true. And it’s really irritating.

Google doesn’t have an AI. It does have complicated decision making software running its cooling centres, one of the many complex software systems that keep the company alive every day. Most of this decision making is automated using traditional software development techniques. Lately, more of it is using machine learning models to make decisions faster than people could do.

What is irritating about this is that it distracts people from the real problems that AI is causing. Hard social problems such as the potential loss of jobs to automation, the bias inherent in any machine learning algorithms, and the concentration of this immense power in corporate hands with no oversight, are demanding attention.

These problems are complex and require lots of thinking and discussion by people to enable society to address the effects of powerful technology. We are poorly served by click-bait headlines in preparing for the artificial intelligence future.

Kategorie: Transhumanismus