I hadn't heard the RLHF feedback loop argument before, but it seems like a solid explanation for all the bad ticks LLMs have when writing and why it's so hard to break them out of it. All of that stuff... "That's not…
Nice thanks for sharing. Just curious, what specifically was the problem you ran into that inspired you to build this?
I hadn't heard the RLHF feedback loop argument before, but it seems like a solid explanation for all the bad ticks LLMs have when writing and why it's so hard to break them out of it. All of that stuff... "That's not…
Nice thanks for sharing. Just curious, what specifically was the problem you ran into that inspired you to build this?