A::B Prompting Challenge: $10k to prove me wrong!
# CHALLENGE
Develop an AI prompt that solves random 12-token instances of the A::B problem (defined in the quoted tweet), with 90%+ success rate.
# RULES
1. The AI will be given a random instance, inside a
A::B Prompting Challenge: $10k to prove me wrong!
# CHALLENGE
Develop an AI prompt that solves random 12-token instances of the A::B problem (defined in the quoted tweet), with 90%+ success rate.
# RULES
1. The AI will be given a random instance, inside a
First day update: x.com/victortaelin/s…
@VictorTaelin Step 1: Write a script that gives tens thousands of examples and answers. Step 2: Fine tune a model on this data. Step 3: Release the model publicly. Meets all requirements. Demonstrates nothing of value besides that LLMs can be trained well on hyper-specific tasks.
@VictorTaelin You need to specify that the AI cannot write a program to solve the problem. There are 2 questions, can an AI simulate the answer if they iteratively follow the steps of the algorithm by printing out each state change. And can they do it without printing state change.
@VictorTaelin may I ask AI to generate python script to solve this problem?
@VictorTaelin those are *all* requirements? so any model?