Governance by bot
What does the rise in artificial intelligence and machine learning mean for school governance?
The next big revolution in tech is likely to be artificial intelligence and machine learning. You may be more familiar with this concept as ‘the one where the robot steals your job’ but to put it more simply, it's where computers begin to solve problems without being told how to.
GovernorHub's Chief Technology Officer, James Sharp, has been a little obsessed with AI recently and its potential to change the world of work and much more. He recently wondered whether AI will ever completely replace school governance. It’s a very interesting (OK, perhaps a tad frightening) proposition that got us thinking.
To find out, we decided to interview the AI that we've been working with at GovernorHub and ask its thoughts on the issue. For comparison, we asked the exact same questions of James. You can decide for yourself which statements come from the human and which from the robot...
What is the function of school governing boards in the UK?
Write a paragraph explaining the function of school governing boards in the UK:
1. School governing boards in the UK play an important role in ensuring that schools are run effectively and in line with the law. They are responsible for setting the strategic direction of the school, approving the budget, and appointing the headteacher. Governors also have a duty to monitor the performance of the school and to challenge and support the headteacher.
2. School governing boards in the UK have three core responsibilities. They’re there to ensure the school has a clear vision and direction, act as a mechanism for holding school leaders accountable and to make sure the school is financially responsible. More broadly, they’re a way of ensuring that a school’s many stakeholders are represented and, much like with many company boards, a way of bringing in appropriate external expertise.
How will AI change the world?
Write a paragraph explaining how AI is likely change the world:
1. AI is effectively computers doing those messy tasks that traditionally only humans could do. For example recognising a bird in an image, transcribing audio, writing poetry. Over the last few years huge strides have been made using a technique called “deep learning” which is basically (massive simplification alert) creating artificial brains. We now have AI computer systems creating artwork, writing (terrible) poetry, performing real time language translation, designing engineering components, composing music etc etc. Recent “conversations” with AI systems have had people wondering whether they’re actually sentient. Sentient or not, the fact that we’re in this position is remarkable, and progress only seems to be accelerating. Needless to say, the effect of this on job markets, economies and our general way of life is going to be profound.
2. I think AI is going to change the world in a number of ways. First, I think it is going to change the way we interact with technology. Right now, we are still in the early stages of AI development, and most of our interactions with AI are through simple tasks like asking Siri to set a timer or asking Google to give us directions. But as AI gets more sophisticated, I think we will start to see it playing a more central role in our lives. It will become our personal assistants, helping us with everything from our work to our personal lives. Second, I think AI is going to change the way we live and work. Right now, there are already some jobs that are being replaced by AI, like customer service representatives or data entry workers. But as AI gets more advanced, I think we will start to see it replace even more jobs. For example, jobs that require a lot of repetitive tasks or that are low-skill and low-wage are especially susceptible to being replaced by AI. This could have a dramatic effect on our economy and the way we live our lives. Third, I think AI is going to change the way we think about intelligence itself. For centuries, we have thought of human intelligence as the highest form of intelligence. But as AI gets more advanced, it is starting to challenge that view. Some experts believe that AI could eventually surpass human intelligence, and that has profound implications for our future. So, these are just a few of the ways I think AI is going to change the world. It is a technology that is still in its early stages, but it is already having a major impact on our lives.
What would school governance performed by AI look like?
Write a paragraph explaining what school governance in the UK would look like if it was performed by AI:
1. School governance is not just a single process and I don’t think we’d see an AI performing it all. In a society where we place value on diversity of practice, setting the strategic direction of the school seems like a fundamentally human-based decision (we’re educating our human-kids after all). Handling e.g. complaints, recruiting headteachers, supporting the headteacher - I think these will all need a human element too. But a lot of other aspects of governance could be, and I suspect will be, handled by sufficiently advanced computer systems. For example, ensuring the school is compliant with regulations, performance monitoring, data analysis and answering those Ofsted style questions like “how do you know safeguarding is effective”. In short, I think human-governance would be a much less onerous job than it is now, and school oversight would be a lot more consistently robust, and largely handled by AI.
2. If school governance in the UK was performed by AI, it would likely be a much more efficient and effective process. AI would be able to quickly and accurately gather data on the performance of the school and make decisions based on that data. AI would also be able to identify patterns and trends that might miss. However, it is important to note that AI would not be able to replace human governors entirely. Human governors would still be needed to provide oversight and to ensure that AI was being used in the best interests of the school.
How will the AI make its decisions and what could go wrong?
Write a paragraph explaining how AI makes good decisions based on available data. What are some of the pitfalls?
1. AI makes good decisions based on data by looking for patterns and trends. It can process data much faster than a human can, and it can identify patterns that a human might not be able to see. For example, if a school was considering changing its curriculum, AI could quickly analyse data on student performance and identify which curriculum would be most likely to improve student outcomes. AI can also make decisions based on probabilities. For example, if a school was considering implementing a new policy, AI could look at data on similar policies that have been implemented in other schools and predict the likely outcome of the new policy.
However there are some pitfalls to using AI to make decisions. First, AI is only as good as the data it is given. If the data is inaccurate or incomplete, the AI will make decisions based on that data, which could lead to suboptimal outcomes. Second, AI can sometimes be biased. This can happen if the data that is used to train the AI itself is biased. For example, if an AI is trained on data that is mostly from white, middle-class students, it could be biased against students from other backgrounds. Finally, AI is not perfect. It can make mistakes, just like humans can. So, it is important to have a system in place to catch and correct errors that the AI makes.
2. A good AI system has all the advantages of traditional computer software, namely the ability to do errorless computation and calculation across incredibly large data sets, but also the “intelligence” aspect of reasoning, pattern matching, prediction and taking action on top of that. Humans are not nearly as good as computers when it comes to handling large quantities of data, and so, for a given task, we have to analyse and slice the data down to something manageable before doing “intelligence” on it. Without these limitations AI systems should be able to make much better decisions in general. It doesn’t, however, get away from the fact that if the underlying data set is biased then decision making will be too.
AI governance
Hopefully this has given you a (perhaps frightening?) glimpse into the future and something to think about.
For those who wish to know whose answers are whose, here is the big reveal:
1. AI (1), James (2)
2. James (1), AI (2)
3. James (1), AI (2)
4. AI (1), James (2)
Share this article
Share on GovernorHub
Post your comment
Comments
No one has commented on this page yet.
RSS feed for comments on this page | RSS feed for all comments