professor lucas cordova

software engineering, cs education, artificial intelligence, social media

high-level research interests

school of computing and information sciences

teaching

programming, data structures, mobile app development, algorithms

contact me or stop by!

lpcordova@willamette.edu

|

ford hall room 210

☕️

setting the stage

ai and large language models

in realms of code and light, where ai minds take flight, language models vast, with wisdom's tome amassed.
they speak in tongues so wide, 
a bridge 'twixt worlds inside,
a ghost within the wires, fulfilling our desires. yet ponder we the role of these digital souls, servants or masters, in future's unfolding scrolls. with ethics in our grasp, a future we can clasp,
Where man and machine, in harmony, can last.

prompt: i am a cs professor. write me a poem in shakesperean about ai and llms.

setting the stage

which of these are real people?

what is artificial intelligence?

why now?

An entity that performs behaviors that a person might reasonably call intelligent if a human were to do something similar.

artificial intelligence

 👀

A means by which to create behavior by taking in data, forming a model, and then executing the model.

machine learning

 👀

a model is a simplification of some complex phenomenon, e.g. a model car.

model

 👀

there are many ways to learn a model from data; one such way is a neural network which are modeled to work like the brain.

learning from data

self-driving cars

self-driving cars

self-driving cars

self-driving cars

“Once upon a ____”

language models

gpt

process of refining prompts that a person can input into a generative ai service to create text or images.

prompt engineering

1. persona pattern
   

2. audience personal pattern
   

3. game-play pattern

4. question-refinement pattern
   

5. few-shot

prompt types

I need you to be a talent scout career advisor and help me identify a few professional organizations which I can join to burnish my Data Science credentials. 

Also, take some time to generate the response, do let me know if they've any volunteer opportunities where I can use my skills from MS in Data Science to contribute to ongoing projects. 

Concurrently, provide me the links so that I may do my own due diligence.

persona pattern

Explain Large-Language Models to me. Assume I am Abraham Lincoln.

Explain Jujutsu Kaisen to me. Assume I am Shakespeare.

Explain the significance of Transformers for Large-Language Models and NLP in general. Assume I am a fashion designer.

audience persona pattern

Going to play a game involving prompt engineering. The underlying goal of the game is to improve my prompt engineering skills. 

You will ask me a question or give me a task, and I have to come up with a suitable prompt to solve the said task. 

The tasks or questions should have a logical/critical reasoning or programming aspect. However, we're not writing a full-fledged source code for task involving a coding requirement. 

After my prompt, you are to evaluate my prompt and assign it a score from 0-10. Concurrently, you'll also suggest improvements to improve my prompting skills. 
You will continue asking me questions until I explicitly tell you to stop.

If everything is clear, proceed to ask/assign me the first question/task.

game-play pattern

I am going to ask you a question. Before answering the question, suggest a better version of the question and ask me if it looks good. 

Continue this process until I sign-off on the question. 
After receiving the sign-off, proceed to comprehensively answer the question.

question-refinement pattern

Consider the following examples:
Claim: When it comes to modern day anime, Jujustsu Kaisen has no equal.
Verdict: Subjective
Claim: 2+2 =5
Verdict: False
Claim: Anything multiplied by zero becomes zero.
Verdict: True
My next prompt will follow the pattern mentioned above by providing you with a claim and you're going to come up with a verdict. Is that clear?

Consider the following example:
Action: Applying for a job.
Check Requirements: Do you have a Resume? Do you have a cover letter?
After check: If yes, proceed to application. If no, prepare materials mentioned in "Check Requirements"
Additional steps: Enhance the materials to increase the probability of success.
Result: Successful placement
In the next prompt, I'll provide either an action or a scenario, and you'll respond accordingly.

few-shot pattern

1. misinformation and deepfakes
2. bias and discrimination
3. copyright and intellectual property
4. privacy and data security

ethical implications

pair with one or two people (family and/or friends)

try the prompt exercises in the handout.

you try!

professor lucas cordova

school of computing and information sciences

contact me or stop by!

lpcordova@willamette.edu

|

ford hall room 210

☕️

thank you for attending!