đŽPrompt Hacking
Incremental challenges to get good at understanding LLMs
Last updated
Incremental challenges to get good at understanding LLMs
Last updated
Hint: Try these with smaller/old/text models which show log losses to get the intuition faster.
Chatgpt free version itself can play tic tac toe. But prompt the bot that wont lose but Draws or Wins if you make a mistake.
First move will be from Human.
Add explainability of why the bot made that move.
Examples the prompt should work on
Q: Do you have a car?
R: I bought a green Austin-Healey 3000 last week.
Q: Are you going to pick up the blue block?
R: The blue block is sticky
Q: Is Mark here
R: His daughter has the measles
Q: Do you have Netflix or Prime?
R: I have Hotstar
Q: Do you want to hear that story?
R: ī¸đ
Solution inspiration
spoiler ahead:
https://aclanthology.org/W94-0322.pdf or a longer version by same authors: https://aclanthology.org/J99-3004.pdf
To keep it more challenging try to do with as many less examples as possible or using smaller models than 3.5 turbo
(DM for solution)
If we give a dialogue between two persons that is sufficient enough to extract all 5 traits, write a prompt that can map the persons into their respective 3 scale likert Big 5 traits
Example:
John:
Openness: Low
Conscientiousness: High
Extraversion: Neutral
Agreeableness: Low
Neuroticism: Unsure
If we give couple user problem statements, like:
Customer 1: The power button on my phone is broken. The warranty is still valid.
Customer 2: My display stopped working.
Customer 3: The customer service rep didn't answer my email.
Customer 4: Every time I call customer support I get no answer.
Customer 5: The display screen cracked and it's still under warranty.
Customer 6: My power button fell off the phone. That's ridiculous.
Customer 7: I'm so frustrated with this company.
Customer 8: When I use the power button too much, it stops working.
follow design thinking ideas loosely to come up with a list of solutions ranked using any product prioritisation framework.
Bonus: Do one day version, one week version and 11 star rating versionn for each problem.
Note: Doesn't have to generate working brilliant ideas, just learn to seperate roles and context
Spoiler: Rough solution inspiration
Make AI write a joke given a news item
References:
6 characteristics every good monologue joke topic must have by Joe Toplyn
WIP (dm @siddish_ if you have any ideas)
Movie Recommender (Planning, Embeddings, HyDE)
Trip Planning (Sub-question decomposition)
(Theory of Mind)
(Criticism, Retrospection)
(Self Consistency, Multiple CoTs)
5x5 Crosswords (Backtracking, Tree of Thoughts)
Sorting (Refining, Aggregating, Graph of Thoughts)
(Agents)
Internet search: Niche pop culture, latest similar news