What Should We Expect From ChatGPT?
The chatbot has made waves over the past couple of months for being able to answer queries in a conversational tone. CS professors discuss what it can and cannot do correctly.
OpenAI’s ChatGPT is an artificial intelligence (AI) chatbot that is trained to follow the instruction in a prompt and give a detailed response. It is built upon GPT-3, a type of large language model (LLM) that predicts and generates text. Given a sequence of words, it will predict the word that has the highest probability of following next (kind of like autocomplete). These models are trained on huge datasets that allow them to generate answers to questions. ChatGPT works quickly and gives answers within seconds, and it also learns from every interaction and improves daily.
It can create a letter to your super asking for a repair to be done, write code and fix bugs, and suggest plot summaries for novels. But that does not mean that it is perfect. The problem with LLMs is that they can “hallucinate” and make things up. ChatGPT is guilty of this; some of the answers in its outputs do not even exist. It is also not trained to be truthful and it answers queries with a lot of confidence and authority, which is worrisome.
It is being compared to the last great tech disruption–the internet’s onset in the 1990s. We asked CS professors what the technology could do and how to use the tool the right way.
I have been using GPT-3 for over two years now. It is the underlying model behind my cricket search app for ESPN.
The original interface was cumbersome and needed an analyst who could use specialized programming languages to access the answer.
We developed AskCricInfo, which takes human input–questions or search queries–and converts the queries into a structured language like SQL that machines understand. The technology can “translate” the question into a programming language, find the answer, and quickly send it back to the user.
It is an excellent example of the power of underlying technology and what the tool can do. ChatGPT is very interesting. It is the first chatbot that makes “intelligent” and engaging conversations. There are definite use cases for making it a very effective teaching tool. It is up to the instructors to imagine a world where something like ChatGPT will always be available and teach students how to use it effectively. A lot can go wrong with ChatGPT- primarily because of its design that makes it bullshit confidently. But that is a problem with all LLMs, not just ChatGPT.
ChatGPT and the technology it is built on, GPT3, are game changers. With them and the other large language models that have recently emerged, models can now produce extremely fluent text. They are also able to perform a variety of tasks in a way that was not previously possible. And there are many situations in which they can be used to help us do things that we previously found tedious. But they are not able to do as much as we might initially have imagined. They have limitations that are not always immediately obvious, and researchers are taking the time to study them so that we can accurately characterize what they can and cannot do. Nonetheless, they change how we do research in the natural language field and how we build new models to carry out other tasks.
I think we need to learn how to incorporate them into our teaching because they are here to stay. Students know about them and will know how to use them. We will need to think creatively about how to teach students what these tools do well and what they do poorly, when they can be used as a tool to aid in research, and situations in which it would be dishonest. I imagine situations where we ask ChatGPT to answer an essay question, ask the student to critique the essay and identify what it does poorly, and then ask the student to write an essay that goes beyond what ChatGPT can do.
The worst problem with ChatGPT is that it is not always truthful. In fact, it may often lie or hallucinate facts. It does this very fluently, making its lies sound very plausible. This is quite a barrier to use in a real-world situation unless it is used by someone who knows what is correct, what is not, and can sift the good from the bad. Technology constantly changes, though, and it is a problem that researchers are actively working on.
I asked ChatGPT about AI language models, and this is the output:
AI language models like ChatGPT, its competitors and successors represent a significant advancement in the field of Natural Language Processing (NLP). These models have the ability to generate human-like text based on a massive amount of input data, making them useful for various applications such as chatbots, question-answering systems, and content generation.
However, it is important to note that despite their sophisticated capabilities, they still have limitations and may generate outputs that are inaccurate, biased, or inappropriate. It is crucial to ensure responsible development and deployment of these models to maximize their benefits while minimizing potential harm.
The above demonstrates my thoughts more than I could otherwise express. In particular: it is already useful, but often not out-of-the-box, but I am a techno-optimist and believe even more usefulness is coming.
As a former judge in high school debate competitions, it reminds me of the most eloquent contestants, who would, if they needed to, lie through their teeth without missing a heartbeat. For instance, in response to this prompt, “What could go wrong with tools like ChatGPT?”, it writes:
There are several potential risks associated with the use of AI language models like ChatGPT:
Bias: AI models are trained on large amounts of text data, which may reflect societal biases and lead to biased outputs.
Misinformation: AI models may generate false or misleading information, which could have serious consequences if relied upon.
Privacy Concerns: AI models process large amounts of personal information, raising privacy and security concerns.
Misuse: AI models may be used for malicious purposes, such as spreading hate speech, fake news, or conducting phishing attacks.
Job Loss: AI models may automate certain tasks, leading to job loss in industries that rely on those tasks.
Therefore, it is important to carefully consider the potential risks and consequences of AI models and to develop and deploy them responsibly to minimize potential harm.
These are all valid points, but more context needs to be considered:
- When it comes to bias, chatbots are worse than the best other (human?) alternatives but much better than the median ones.
- Misinformation is a big problem when compounded by misuse, and we can see that happening now with stories posted online.
- Privacy concerns depend on who has access to the data in ChatGPT and what can be done with it. But given that we all carry powerful tracking and sensing devices 24/7, our privacy is already weakly protected against powerful actors.
- Some attention-seeking blogs and websites overstate the job loss point. Many jobs will become more efficient; many jobs will change; many jobs will be created, and, yes, many will be lost. People will adapt, and we will all be better for it.