Here, COLI is assembling a list of introductory information, tips, and resources concerning artificial intelligence, and it's possible implications for pedagogy and scholarship.  This resource is tentative, certainly incomplete, might age rapidly, and probably (at any point in time) a little wrong in places.  

Understanding Large Language Model (LLM) Generative Artificial Intelligence (AI)s

...

• recipes for food dishes,

• lesson plane for secondary school science classes,
• a cover letter accompanying a job application,
• a thank-you note,
• an essay on the development of the Code Napoleon,
• simulate a fifteen-year-old blogger reviewing a video game,
• code a module or particular task within a computer program.

In the following box is a copy of a conversation with LLM AI Google Bard describes itself as follows:, in which it describes itself.  Bard's description is helpful, but it also provides a basic example of what LLM AIs can do in response to prompts. 

Any successful LLM AI production requires a carefully written prompt from the user.  This must properly describe the user's intent, and if the AI's response is not to be dependent on its training corpus, it the user's prompt must supply relevant data as well.  Already, education and technology experts speak of "prompt engineering" as a probably skill necessary for students in the future, but it remains to be seen whether that is true, as these tools (more or less) evolve.

In COLI, we've taken to describing an LLM AI as a machine that simulates a person who knows what they are talking about responding to questions.  

Limits to LLM AIs

Importantly, the current LLM AIs have limits.  If you ask them to describe those limits, they will usually enumerate.  For example, when asked why it occasionally gets things wrong, ChatGPT replies that its answers will reflect shortcomings in its training data: biases, incomplete or wrong information, or ambiguity.  Plus, it may struggle to interpret language within that training corpus.  

...

This tentative guide is concerned with Large Language Model AIs, which are (at the time this is written) the most powerful artificial text generation tools available.  Other tools, be it a customer service chatbot, a grammar assistant, or even the non-playable antagonist and their henchmen in video games, can be considered artificial intelligence, although they generally follow much simpler routines than LLM AIs.  However, in COLI we expect to see in the next several months and years LLM AI-powered tools and features appear across the internet, in software and on mobile devices.  So this distinction may not be relevant over time.  

Pedagogy 

Each discipline will need to determine the extent to which LLM AIs compel adaptation or alteration of their curriculum.  Each faculty member will also likely need to consider the relationship between their teaching style and methods, and LLM AIs.  However, here is a list of things that might spur some inspiration.

...

To generate answers similar to these, here's the prompt: What are some assignments for a undergraduate university (discipline) course that have students practice or demonstrate things LLM AIs cannot do for them?

Like a lot of responses from LLM AIs, these suggestions are typically vague.  And an LLM AI–ChatGPT, for example-- may attempt to simulate the things it tells it can not do very well, if prompted by you (or a student.)  Therefore, the faculty member needs strong command of any disciplinary knowledge involved in the assignment, if they are to assess student work for accuracy or integrity.  But these can be a good starting line for your process of thinking about assignments that are "AI proof"

...