Re:Large language models (e.g., ChatGPT) as research assistants
by drycabinet on Saturday April 27, 2024 @02:15PM
(#40182151)
But some random word in its response can trigger an idea in your mind. Getting an idea from a conversation is not always about getting it directly. It's already in you and you just wanted a trigger.
Re:Large language models (e.g., ChatGPT) as research assistants
by jprete on Saturday April 27, 2024 @02:39PM
(#40182332)
Rubber-ducking is useful, but nobody gives the rubber duck anywhere near as much credit as AI enthusiasts give to chatbots.
Re:Large language models (e.g., ChatGPT) as research assistants
by littlestymaar on Sunday April 28, 2024 @02:27AM
(#40186459)
You underestimate how much credit I give to rubber ducks ;)
While GPT4 can recognize an innovative idea, I have yet to see it suggest such an idea, or successfully extrapolate or question the idea. If you are beyond the "concept space" of the model, it is not going to help you explore it.