Graybeard
Well-Known Member
A new AI approach?
This is more about manipulating ChatGPT (AI LLM) output to create understandable text from egg-head over complications.
I was thinking about content security and copyright ownership when using programming code created with AI even if you are the one instructing the AI to revise code that was initially created with AI prompts. Chicken and egg conundrum here ...
Quote`` FunSearch (short for searching in the function space) combines a pre-trained (frozen) Large Language Model, whose goal is to provide creative solutions, with an evaluator, which guards against confabulations and incorrect ideas. FunSearch iterates over these two components, evolving initial low-scoring programs into high-scoring ones discovering new knowledge. Key to the success of this simple procedure is a combination of multiple essential ingredients. First, we sample best performing programs and feed them back into prompts for the LLM to improve on; we refer to this as best-shot prompting. Second, we start with a program in the form of a skeleton (containing boilerplate code and potentially prior structure about the problem), and only evolve the part governing the critical program logic. For example, by setting a greedy program skeleton, we evolve a priority function used to make decisions at every step. Third, we maintain a large pool of diverse programs by using an island-based evolutionary method that encourages exploration and avoids local optima. Finally,leveraging the highly parallel nature of FunSearch, we scale it asynchronously, considerably broadening the scope of this approach to find new results, while keeping the overall cost of experiments low ``
Mathematical discoveries from program search with large language models - Nature cutting-edge stuff (supposedly) WTF is this about?
Prompt: Speaking as an a 11 grade computer science teacher explain this statement to your class:
This is more about manipulating ChatGPT (AI LLM) output to create understandable text from egg-head over complications.
I was thinking about content security and copyright ownership when using programming code created with AI even if you are the one instructing the AI to revise code that was initially created with AI prompts. Chicken and egg conundrum here ...
Quote`` FunSearch (short for searching in the function space) combines a pre-trained (frozen) Large Language Model, whose goal is to provide creative solutions, with an evaluator, which guards against confabulations and incorrect ideas. FunSearch iterates over these two components, evolving initial low-scoring programs into high-scoring ones discovering new knowledge. Key to the success of this simple procedure is a combination of multiple essential ingredients. First, we sample best performing programs and feed them back into prompts for the LLM to improve on; we refer to this as best-shot prompting. Second, we start with a program in the form of a skeleton (containing boilerplate code and potentially prior structure about the problem), and only evolve the part governing the critical program logic. For example, by setting a greedy program skeleton, we evolve a priority function used to make decisions at every step. Third, we maintain a large pool of diverse programs by using an island-based evolutionary method that encourages exploration and avoids local optima. Finally,leveraging the highly parallel nature of FunSearch, we scale it asynchronously, considerably broadening the scope of this approach to find new results, while keeping the overall cost of experiments low ``
Mathematical discoveries from program search with large language models - Nature cutting-edge stuff (supposedly) WTF is this about?
Prompt: Speaking as an a 11 grade computer science teacher explain this statement to your class:
