Signing off early for Christmas...
A look at ChatGPT + Other stories that matter
Today is the last edition of Off to Lunch before Christmas. I am signing off early because this week, all being well, our second child will arrive. Off to Lunch will return in the new year!
To thank all Off to Lunch subscribers for your support since we launched in April I am going to pause billing between now and the end of the year. So existing subscribers won’t pay anything for the next month. I have not offered any discounts or promotions on new Off to Lunch subscriptions and instead wanted to offer a discount to existing subscribers. Thank you for all your support. Without it, Off to Lunch would not exist, would not be doing so well and, frankly, would not be as much fun. Thank you for subscribing but also for your ideas and feedback. It’s been brilliant.
The new episode of our Business Studies podcast will go live tomorrow and all subscribers will be notified when it does. It’s a great episode that looks at a new drive by Britain’s universities - specifically Oxford - to turn their world-leading ideas and research into world-leading businesses. This is something that the UK’s universities have not been good at compared to their international rivals in the past, but that is now changing. The format of this episode is slightly different as I speak to three key figures in the story. I look forward to sharing it with you…
As ever, there is a round-up of the stories that matter in today’s edition, which you can find below. One story I wanted to pick-out is all the hype around OpenAI and its ChatGPT technology. ChatGPT is a chatbot/artificial intelligence technology that responds to a wide range of written requests from its user with human-like prose. Think of it as a next-generation internet search engine. It has caused much excitement in the technology world and on social media because it looks to be the most advanced, sophisticated and useful chatbot technology we have seen. Here are some examples of what it can do from people trialling ChatGPT online. It has been writing essays, poems, news reports and more…
This is what the chief executive of OpenAI, Sam Altman, says about it…
I recommend signing up to give it a go yourself. You can do so by clicking here. It is still limited in its capabilities and knowledge. This morning I tried it and asked: “When did England last win the World Cup?” This was the answer I got:
England has never won the FIFA World Cup. They have made it to the finals twice, but lost both times. In 1966, they lost to West Germany 4-2 in the final, and in 1990, they lost to West Germany again, this time by a score of 1-0.
Talk about rubbing salt in the wounds. However I also asked: “Is fusion energy possible?” This relates to a story I link to below. This was the answer to that:
Yes, fusion energy is possible and is considered a promising source of clean, safe, and abundant energy. Fusion is the process by which atomic nuclei combine to release large amounts of energy, and it is the same process that powers the sun and other stars. While fusion has the potential to provide an almost limitless supply of energy, it is also very difficult to achieve and control. Scientists and engineers are currently working on developing fusion reactors that can produce more energy than they consume, but we are not yet at the point where fusion energy is a viable source of electricity.
One other example, I also asked: “Will it snow again in London today?” This was the answer I got to that:
I'm sorry, but I am a large language model trained by OpenAI and I do not have access to current weather information. I am not able to browse the internet or access real-time data, so I cannot answer that question for you. My knowledge is limited to the text that I have been trained on, and I do not have the ability to provide up-to-date information on specific events or occurrences.
But I must finish with this example. This is what I got when I asked: “How can you boost the UK economy outside London?”
There are many ways to boost the economy outside of London, and the specific approach will depend on the specific challenges and opportunities facing different regions. Some potential strategies could include:
Investing in infrastructure: Improving transportation, communication, and other infrastructure can make it easier for businesses to operate and for people to access goods and services.
Supporting small businesses: Small businesses are a vital part of the economy, and providing them with access to capital, training, and other resources can help them grow and create jobs.
Developing local industries: Identifying and supporting key industries in different regions can help to create jobs and drive economic growth. For example, supporting the development of renewable energy in Scotland or the automotive industry in the Midlands.
Attracting new businesses: Providing incentives for businesses to locate or expand in different regions can help to create jobs and stimulate economic activity. This could include offering tax breaks, access to training programs, or other support.
Investing in education and training: Ensuring that people have the skills they need to succeed in the modern economy is key to boosting economic growth. Investing in education and training programs can help to prepare people for the jobs of the future and support economic growth.
For further reading I recommend a piece from Big Technology on Substack. This looks at why OpenAI, which was founded in San Francisco in 2015 by, among others, Elon Musk, has taken the lead on this technology, why Google missed it, and how sophisticated chatbots could change the way we search for information on the internet. You read it here. I also recommend a piece from MIT Technology Review on how Meta’s attempt to launch a technology similar to ChatGPT - called Galactica - failed. In short, it confidently presented statements as facts when they were incorrect or riddled with bias. This has been a big problem for AI technology so far. You can read more here.
ChatGPT offers a glimpse of how AI and the sophisticated use of data may be integrated into running businesses and making decisions. My interview with Ed Smith, the former chief selector for England cricket, looked in detail at how humans can work alongside data and AI to make decisions. Smith was using data, other sophisticated technologies and trialling AI while working for England. He put a lot of thought into how he could add value to his role on top of the data and algorithms that were pointing to players to select and decisions to make. You can listen to the Business Studies episode here.
Evidence from a range of fields - such as chess - suggests that humans working alongside AI technology is more powerful than humans on their own or AI on its own. Humans are better at the overall strategy. As Smith says in the interview and in his book, Making Decisions, modern technology means that some human skills will be more valuable than ever…
Other stories that matter…
Microsoft has agreed to buy a 4 per cent stake in London Stock Exchange as part of a 10-year partnership to provide data, analytics and modelling support (Investegate)
The UK economy grew by 0.5 per cent in October after bouncing back from the extra bank holiday in September due to the Queen’s funeral. The economy had been expected to grow, but not by as much as this (The Guardian)
Channel 5 is opposing proposals for longer advert breaks on ITV, which would boost revenues for the broadcaster (Telegraph)
US scientists are claiming they have made a big breakthrough on fusion energy. We will get the details on Tuesday. Until then, there are a lot of questions about what this could mean for clean energy (FT)
Coal plants in the UK are on standby to provide energy this week as cold temperatures boost demand for electricity and gas (BBC)
Great piece by The Mill on Gordon Brown’s decentralisation proposals. This follows-on nicely from our interview with Roger Madelin. A pivotal part of boosting the economy outside London is getting away from the attitude that “London knows best” and letting cities and towns make their own decisions about where and how to invest (The Mill)
This piece by The Economist on the benefits of France’s high-speed train network - the TGV - makes you think that the debate about High Speed 2 should not be about whether it goes ahead but why has it taken so long and why is it not bigger (The Economist)
The end of the barcode? Amazon is working on camera technology to replace them on items it sells (CNET)
Hollywood experts think Apple TV+, HBO Max and Netflix are the top streaming sites, Bob Iger is the best chief executive, Zendaya is the actor to watch and Ryan Coogler the director (Bloomberg Screentime)
Binance, the biggest online exchange in the world for buying and selling cryptocurrencies, is under growing pressure to reassure investors about its finances after the collapse of rival FTX and boss Changpeng Zhao constantly raising concerns about other platforms (WSJ)
American management professor Adam Grant thinks the four-day week is an experiment worth running and could take off in Europe, if not the US. “If I were a leader, I would be much more excited about 32 focused hours a work than I would 40 distracted hours.” (WSJ)
Sports writer Grant Wahl died on Friday night while covering the Netherlands v Argentina game at the World Cup in Qatar. He wrote an excellent Substack - Futbol with Grant Wahl - and the company has written a tribute to him (On Substack)
Finally, if you haven’t already read it, check out Off to Lunch’s Sunday press review, where I look at what is interesting and likely to be followed in the weekend papers. You can sign-up to read it here
Thanks for reading. If you enjoy Off to Lunch then please share it with others and spread the word. If this newsletter was shared with you then please sign-up below to become a member, get Off to Lunch sent directly to your inbox and contribute to the work of Off to Lunch
Best
Graham
I hope the arrival of the second child goes well. Congrats.