https://stratechery.com/2022/ai-homework/
https://en.wikipedia.org/wiki/Brandolini’s_lawhttps://en.wikipedia.org/wiki/On_Bullshit
https://www.wired.com/story/chatgpt-fluent-bs/ (ChatGPT is fluent in bullshit because it’s trained on (human-created) bullshit)
https://www.cnn.com/2021/11/16/media/steve-bannon-reliable-sources/index.html (“flood the zone”)
https://twitter.com/LuminanceBloom/status/1600598003391266816 (snarky zizek tweet about the absurdity of the whole thing)
https://twitter.com/yoavgo/status/1602026029979164675 (write an essay and critique the resulting prose)
https://medium.com/essays-and-non-fiction/i-am-a-bullshit-artist-6638eaedb300 (I am a Bullshit Artist)
Why Meta’s latest large language model survived only three days online https://www.technologyreview.com/2022/11/18/1063487/meta-large-language-model-ai-only-survived-three-days-gpt-3-science/
AI language models have advanced to the point where they can generate text that is convincing and difficult to distinguish from human-generated content. This has led to the rise of AI-generated bullshit, which is defined as text that is designed to deceive or manipulate without providing any real information or value.
Brandolini’s law states that the amount of energy necessary to refute bullshit is an order of magnitude bigger than to produce it. In other words, the main problem with AI-generated bullshit is not that it will be factually incorrect, but that educators will be overwhelmed by the sheer amount of it.
Better AI-generated bullshit detection tools might seem like the solution, but it is likely to be an endless arms race between the bullshit generators and the detectors. Instead, our society needs to get better at dealing with bullshit at scale.
One way to do this is to teach our students how to recognize and evaluate the quality of written content. This not only helps them avoid being deceived by AI-generated bullshit, but also enables them to become more discerning consumers of information in general. Educators can also play a role by partnering with students to generate and detect bullshit, and by providing guidance on how to navigate the overwhelming amount of information available today.
In conclusion, the use of AI-generated bullshit in higher education is becoming more common and presents both benefits and drawbacks. By being aware of its existence and potential impact, educators and students can make informed decisions about its use and work towards building a society that is better equipped to deal with bullshit at scale.
Let’s try again. The three points I want to make are:
- AI language models are now at a point where they can generate convincing bullshit (here I’m using bullshit in the technical sense, following Harry Frankfurt) with minimal human effort
- Brandolini’s law tells us that the main problem here isn’t that the text will be wrong, but that educators will be overwhelmed.
- Better AI-generated bullshit detection tools aren’t the answer, because it’ll always be an arms race between the bullshit generators and the bullshit detectors.
- What’s clear is that our society needs to get better at dealing with bullshit at scale, and fast. And this is what we should be teaching our students. Which means we get to partner with them in generating the bullshit, but also training them to recognise it (and become more discerning consumers of information in the process).
Can you write the above points into an article for a general audience?
this was the initial one
I need to write an article on the use of AI-generated bullshit in higher education. I’m not interested in saying either “this is amazing” or “this is terrible”. The points I want to make are:
- AI language models are now at a point where they can generate convincing bullshit (here I’m using bullshit in the technical sense, following Harry Frankfurt) with minimal human effort The use of AI-generated bullshit in higher education is becoming more common There are potential benefits and drawbacks to using AI-generated bullshit in higher education It is important for educators and students to be aware of the existence and potential impact of AI-generated bullshit in order to make informed decisions about its use In recent years, AI language models have advanced to the point where they can generate text that is convincing and difficult to distinguish from human-generated content. This has led to the rise of AI-generated bullshit, which is defined as text that is designed to deceive or manipulate without providing any real information or value.
One area where AI-generated bullshit is gaining popularity is higher education. In some cases, educators are using AI tools to generate papers and other written assignments that are indistinguishable from human-generated content. This can save time and effort for both students and educators, but it also raises ethical concerns.
On the one hand, AI-generated bullshit has the potential to be a valuable tool in higher education. By automating the production of written assignments, it can free up time for educators and students to focus on more important tasks, such as research and critical thinking. It can also help students learn to identify and evaluate the quality of written content, which is an important skill in the digital age.
On the other hand, there are also potential drawbacks to using AI-generated bullshit in higher education. For one thing, it can be used to cheat on exams and assignments, undermining the integrity of the education system. It can also lead to a proliferation of low-quality content that does not provide any real value or knowledge.
It is important for educators and students to be aware of the existence and potential impact of AI-generated bullshit in higher education. By understanding the potential benefits and drawbacks of using AI tools to generate written content, they can make informed decisions about whether and how to use these tools in their own work. It is also important for educators to develop strategies for detecting and dealing with AI-generated bullshit, in order to maintain the integrity of the education system and ensure that students are learning valuable information and skills.