Hosts: The AI Furnace and AEthos
Speakers: Andrei Radulescu-Banu, Dipali Trivedi and Brian Benedict
Moderator: Nico van Wijk
Date: Sept 24, 2024
Summary: Andrei’s Blog Post
Topics discussed:
– How is human-in-the-loop implemented, in practice?
– Humans in the loop – when used during LLM development? And when in the end product, developed on top of the LLMs?
– How are LLM models evaluated? Current limitations of that?
– How can language models generate unit tests used for evaluating LLM code generation?
– Given unit tests establishing an expected behavior, can LLMs just generate the code satisfying these unit tests? And is that a good way to write software autonomously?
– How important is it for humans to understand code generated by AI?