by I typed in the question – “explain what ChatGPT is in Cockney style” – and within seconds came the computer-generated response: “‘Ello gov’na! Let me tell you about ChatGPT, the AI language model that it can talk and walk.You see, ChatGPT is a powerful machine that has been trained to understand and generate human speech.
“But be careful, because like any powerful tool, ChatGPT can be used for better or for worse. So, use it wisely and fairly, or you could find yourself walking the plank!
It’s an answer that, I’m sure you’ll agree, started convincingly with Danny Dyer, but ended more Jack Sparrow.
While obviously not perfect, you can see why ChatGPT is causing so much debate. You can ask him to write a sonnet about Sadiq Khan (“So we honor the noble son of London, who works to make his city, shining, one…”) or a one-line summary of Prince Harry’s new book (“A personal and raw account of his mental health struggles…”).
There were even reports that the responses generated by ChatGPT passed the admission test for Wharton’s prestigious MBA course in the United States. It’s a level of sophistication that has many but other enthusiasts concerned, including Microsoft, which on Tuesday announced a multibillion-dollar investment deal with OpenAI, the company that created ChatGPT, to try to outpace its competitors in the AI arms race. . OpenAI, which counts Elon Musk among its early investors, is now valued at nearly $30 billion, quite an achievement for a company with just 350 employees.
ChatGPT uses a “deep learning model,” basically analyzing huge amounts of text on the internet and using that data to figure out how to construct human-sounding sentences.
Meta’s chief AI scientist said that ChatGPT “isn’t particularly innovative,” because its underlying technology isn’t much different from what’s being developed at other companies.
True or not, there’s no denying that ChatGPT is one of the most tangible uses yet of artificial intelligence, the term for software that can do tasks that previously only humans could do (such as writing complex prose), and potentially even outsmart us (like in chess, where no human can beat the latest AI machines).
At the same time as ChatGPT, we have also seen the emergence of AI software such as DALL-E (also by OpenAI) and Midjourney which can generate stunning images and artwork in seconds, the sort of thing that until recently only human beings could have created . I have been writing for years about the potential impact of AI on work and society and how London is at the forefront of this change, thanks to UK companies such as DeepMind, Faculty and Stability AI.
In the same way that automated factories have reshaped the labor market by replacing many “blue-collar” jobs with robots, some experts predict that artificial intelligence will replace a large number of “white-collar” roles. The Bank of England estimates that up to 15 million jobs could be lost in the UK, with administrative and clerical roles among the most at risk because they can be more easily replaced with advanced software. And it’s not hard to think of other potential downsides, like fake news generated by AI or cheating students by asking ChatGPT to write homework. But here’s why I think the future of AI may be brighter than pessimists believe. For many workers, AI software will be a tool that will eventually help us, not replace us.
The future could be brighter than pessimists believe: for many, AI will be a tool that will eventually help, not replace us
See how Microsoft is incorporating ChatGPT into Word and PowerPoint, which means your computer will increasingly be able to do the hard work of writing and putting together presentations, as long as you point it in the right direction.
Google is trying to do the same with Gmail, so it can write emails for you — and they’re apparently planning a chatbot for their search engine to make it easier to find information online.
Another good example is teaching, where engineers are experimenting to see how ChatGPT could be used to grade student work. If these approaches materialize, they could help free people from some of the more boring and time-consuming parts of their work and give us more room to focus on what’s meaningful and important.
But the main reason to be positive is that AI could unlock innovations we couldn’t invent on our own. Perhaps the best case study is here in London, where DeepMind researchers have made startling discoveries in understanding how proteins, the building blocks of life, fold into different shapes. If this problem can be solved, it could lead to new treatments for diseases such as Alzheimer’s and Parkinson’s and potentially allow scientists to develop new sources of clean energy.
DeepMind’s software has analyzed massive amounts of data and spotted patterns much faster than a person could, but this AI computing power was also combined with the brainpower of humans, who used the software’s findings to develop new insights and discoveries. Demis Hassabis, co-founder of DeepMind, says using AI in this way “allows us to be much more creative, to try out many more ideas, often in parallel.” Instead of replacing the scientists, he supplemented their skills.
We’ve already seen ChatGPT listed as a co-author in academic papers – with physicist Kai Polsterer describing AI systems as “hardworking assistants” that can set you free “to do the cool and interesting science yourself”.
What we’re starting to find in science may end up being a better prediction of the future than the vision of a world where robots destroy all of our jobs. It’s a working life with the potential to be much more interesting than we could have imagined, and more creative as well.
I’ll leave the last word to ChatGPT, who gave this answer when asked about the years ahead: “AI can be both good and bad depending on how it’s designed, developed, and used.”
Sounds suspiciously like the answer of a slimy politician, but it’s probably close to the truth.
