I learned so much from this post. The tenacity of your analysis is striking. You identify the complicated limitations of LLMs, which try as I might, I can’t use for any of the research objectives I have in my work. The concept of the RL agent is exciting. I got a feel for what it might do and why it can do it. I can imagine how it would work in a journalism environment—my field—and see how remarkable it would be for managing reporting projects in investigative team work. Many thanks for your brilliance, Saba.
I learned so much from this post. The tenacity of your analysis is striking. You identify the complicated limitations of LLMs, which try as I might, I can’t use for any of the research objectives I have in my work. The concept of the RL agent is exciting. I got a feel for what it might do and why it can do it. I can imagine how it would work in a journalism environment—my field—and see how remarkable it would be for managing reporting projects in investigative team work. Many thanks for your brilliance, Saba.