Agreed. What would make you less skeptical? We typically do not look into the code within the software that we install in our systems today - so there is some level of trust already.
This resonates with me too. However, as LLMs increasingly shift towards more "agentic" capabilities—where they're not just generating code but also executing it and performing actions beyond just text generation—I'm thinking: where do we draw the line? What should startups and developers working on such systems do to be trusting?
I believe "extract notions and summarizing" is what will be more useful. Also I believe achieving this would give us much better search inside chats. This should be totally possible with the current state of NLP we have.
Just lazy to do it myself ;)
My thoughts as well. With the recent advances doing image similarity and content based search should be fairly simple and probably more effective with pre-trained convnets.
I wonder if implementing a "chain of responsibility" -- kinda falls into my third scenario -- will improve trust levels for code generated by LLM.