15 Comments
User's avatar
Andrew Barban's avatar

Great post, and cudos to both of you, Joel and Karen. Very thorough and well explained. I agree with your partnership model. You are responsible for your own content. How you get there, I am not really worried about. It will be interesting to see how the "ethics" of all this will shake out. Thank you for taking the time to do this and post it.

Expand full comment
Karen Spinner's avatar

Thanks so much! Agree this is an ethical gray area. Ultimately, I’d love to see more transparency (and less stigma) around writing with some level of AI assistance.

It’s also important to remember that people (via content farms) have generated some pretty awful content all on our own. 😆

Expand full comment
Hodman Murad's avatar

Nice post, you two! Your finding that simple, iterative prompting with a writing sample often outperforms expensive tools is both counterintuitive and practical. It suggests the real skill isn't finding a magic bullet, but in crafting a better, more collaborative process with the AI.

Expand full comment
Karen Spinner's avatar

💯 I was honestly surprised that the long prompts weren’t obviously better!

Expand full comment
Joel Salinas's avatar

Thank you!

Expand full comment
Ryan Sears, PharmD's avatar

Very rigorous examination of this pervasive phenomenon. Interesting insight that more detailed prompts doesn’t necessarily lead to better results.

Well done, Joel and Karen!

Expand full comment
Karen Spinner's avatar

Thank you! ❤️ I was definitely surprised when results from the longer, more specific prompts weren't significantly better. Of course, with non-deterministic models, YMMV.

Expand full comment
Ryan Sears, PharmD's avatar

I’ve had the same impression but haven’t done this kind of testing to back it up.

As “non-deterministic” as LLMs may be, they’re very determined to sprinkle em-dashes everywhere they can 😂

Expand full comment
Melanie Goodman's avatar

Great detailed article Joel and Karen again sure will tap into the frustrations of many. The breakdown is seriously impressive -proper rigour and clarity in a space that’s often clouded with jargon and hype. I haven’t tried your humaniser yet as I don’t use Claude!

Expand full comment
Joel Salinas's avatar

I think it’s time to get a free Claude account 🤓

Expand full comment
Melanie Goodman's avatar

On it 😂

Expand full comment
Joel Salinas's avatar

🥳

Expand full comment
Karen Spinner's avatar

Thank you! 🤗 For me, one of the biggest takeaways was that "humanized" writing that could bypass AI detection was not necessarily good, publishable writing.

Expand full comment
Chris Tottman's avatar

Your work rate is insane! I don't know how you do it Joel ✨ inspiring. I'm v thankful as I get to enjoy your work 😁

Expand full comment
Joel Salinas's avatar

Much of this was Karen, but thanks! 😊

Expand full comment