Even if we are not surrounded by self-driving cars (yet), AI is advancing in many domains. It reminds me of the spread of computers and internet in the last few decades where the cumulative progress looking back on the past few decades seem like huge leaps while new technology seem so incremental.
When looking at the history of AI, there have been several paradigm shifts which have led to exponential gains in AI capabilities. Some notable paradigm shifts include the development of deep learning, which has allowed machines to learn complex tasks by training on large amounts of data, and the development of reinforcement learning, which has allowed machines to learn by trial and error. While the daily progress of AI may seem slow, the overall progress of AI has been exponential.
That last paragraph, believe it or not, was written by AI using the last sentence of the first paragraph as the pattern to match. You can try it too at https://beta.openai.com/playground
Some other prompts I played around with:
Prompt: How will climate change impact crop insurance?
AI Model text-davinci-002: Crop insurance is likely to come under increasing pressure from climate change in the future. Insurance companies will be forced to account for the increased risk of crop failure due to extreme weather events, and this is likely to lead to higher premiums for farmers. In some cases, insurers may even refuse to provide cover for certain crops in areas where the risk is deemed to be too high. This could have a major impact on farmers, who may be forced to switch to less risky crops or adopt new farming practices in order to obtain cover.
Prompt: How will governments respond?
AI Model text-davinci-002: Global climate change will require a fundamental rethinking of the way governments design and operate programs to support farmers. Crop insurance is one area where government action will be needed. The impact of climate change on crop insurance will vary depending on the type of insurance, the crop, and the region. For example, insurance for wheat grown in the Canadian Prairies will be different than insurance for rice grown in Asia. Governments will need to take into account the increased risk of extreme weather events when designing crop insurance programs. They will also need to account for the fact that some areas will become too hot or too dry to grow certain crops. In some cases, government support will be needed to help farmers transition to new crops.
How much of what we read in the future will be produced by AI? It might feel a little unsettling to contemplate living in a world where the media we consume will be mostly AI derived (rather than just spam and twitter bots). And that future might be coming much sooner than we are prepared for.