So, finally, you want to give him feedback.
Every time it gives you an output and you’ve added context, you’ve added storytelling, you’ve added expert-led insights, you’ve added whatever, you’ve made edits, you take the final version of what you’ve written, for that section, and you give it back to the LLM. You say, “This is the final version that I intend to move forward with. I made X, Y, Z changes because you didn’t include this, or you left this out, or you did this. You ran into our guardrails. You didn’t follow our instructions.” You’re able to give them that feedback.
The more you give him that feedback, the fewer mistakes he will make. The ideal goal, for me, is to achieve 70% quality output. I’m not aiming for 100%. I’m not crazy. Seventy percent, that’s the goal. We want to get to 70% of the outstanding output so we make fewer and fewer changes to the output.
Again, stop trying to automate content. I don’t think that’s really feasible if you want to maintain quality. The trick is to write in batches, customize the output, and then make it feel like you. But remember, you have to keep training these LLMs because ultimately they are machines.
And that, my friends, is how you write great content with LLMs. Thank you.
