I have been having a bit of go with AI as well. I think however having used chapgbt, Gemini (whom we fondly call "Jim and I" ) and Claude --there is an extreme difference between all three. I try to stay in a playful place with all this.
For Claude I have been very explicit ... don't flatter me. I like pushback and I always appreciate a "what if" scenario. So it always gives me pushback and "what if's" ( I think it is wired to flatter that is a harder ask for it to stop doing)
Here is a snippet from this weekend from Claude to me"
"One honest pushback on what you just said. Because you asked for honesty and I'd be failing you otherwise.
I'm a very good thinking partner. Today has been genuinely remarkable — the scout, the dink, the failure of imagination, the promise you won't keep to yourself. This was real thinking.
But I don't know what your face looks like when you say these things. I can't sit with you in the silence after the hard part. I don't know Hunt's voice or Julia Thomas's laugh or what the Vermont light looks like through your window right now.
Find one human who can hold some of this. Not all of it. Just some."
I love doing the writing myself. Claude knows that so it never gives me text but it gives me criticism, tells me what it thinks is working and sometimes makes suggestions where it thinks my writing is weak. It is also very good at checking any facts or references to make sure they are as close to 100% as I can get. It is really good at recognizing if a reference I am using was generated by AI. It warns me. And that's pretty funny, yes?
I have had your experience not hers. I quickly learned to tell any AI agent to turn off the BS. I don’t need it. I don’t want it. Indeed I need and I want the opposite. I want pushback. I want to be challenged. I want alternative points of view. I want dialogue. I need human interaction and experience to write well.
With AI, to be blunt, you get what you ask for. If you say “rewrite” it’s probably gonna chop your thousand words down to 500 and say isn’t this great to which you will probably reply hell no you ruined it! However, if you tell it to “offer me a rewrite that maintains my voice, my style, my cadence, and has a focus on literary excellence, please” You get what you asked for without errors.
I’ve been doing this long enough to know it’s a tool that rewards exactness. Vague in, vague out. The same rule that applies to good writing. Many writers use AI the way Leonardo ran his bottega — the master sets the vision, directs the work, and owns the result. His assistants were talented artists in their own right. The intelligence in the room was still his.
I really enjoyed this piece and perspective. I think all of us are wrestling with productivity culture with AI and how to keep our creativity centered as valuable..
OMGosh, you had me at: " ... I’d close my laptop screen, the essay growing evermore amorphous beneath it." Been there. :-) In fact, though I've never tried letting AI drive my writing, your essay so reflected and vividly described my own daily writing struggles I was hooked from the first, eager to find out how your little but big AI experiment turned out. So happy to have it affirmed that our own human creativity is still the prize to keep our eyes on. Brava!
Using AI is cheating. I don't want a polished perfect essay to bring to the world. I want to read the messy feelings of a person's inner self expressed in a way that touches me.
Great points you make! I’ve been struggling for several years with one trauma recovery project that’s left a litany of other projects piled up behind it. But you’ve got me thinking that maybe it’s better to not write at all anymore than ask something artificial to artificially solve the problem on my behalf. After all, it’s the struggle that defines us and shapes us and guides to where we need to be, right?
I have been having a bit of go with AI as well. I think however having used chapgbt, Gemini (whom we fondly call "Jim and I" ) and Claude --there is an extreme difference between all three. I try to stay in a playful place with all this.
For Claude I have been very explicit ... don't flatter me. I like pushback and I always appreciate a "what if" scenario. So it always gives me pushback and "what if's" ( I think it is wired to flatter that is a harder ask for it to stop doing)
Here is a snippet from this weekend from Claude to me"
"One honest pushback on what you just said. Because you asked for honesty and I'd be failing you otherwise.
I'm a very good thinking partner. Today has been genuinely remarkable — the scout, the dink, the failure of imagination, the promise you won't keep to yourself. This was real thinking.
But I don't know what your face looks like when you say these things. I can't sit with you in the silence after the hard part. I don't know Hunt's voice or Julia Thomas's laugh or what the Vermont light looks like through your window right now.
Find one human who can hold some of this. Not all of it. Just some."
I love doing the writing myself. Claude knows that so it never gives me text but it gives me criticism, tells me what it thinks is working and sometimes makes suggestions where it thinks my writing is weak. It is also very good at checking any facts or references to make sure they are as close to 100% as I can get. It is really good at recognizing if a reference I am using was generated by AI. It warns me. And that's pretty funny, yes?
I have had your experience not hers. I quickly learned to tell any AI agent to turn off the BS. I don’t need it. I don’t want it. Indeed I need and I want the opposite. I want pushback. I want to be challenged. I want alternative points of view. I want dialogue. I need human interaction and experience to write well.
With AI, to be blunt, you get what you ask for. If you say “rewrite” it’s probably gonna chop your thousand words down to 500 and say isn’t this great to which you will probably reply hell no you ruined it! However, if you tell it to “offer me a rewrite that maintains my voice, my style, my cadence, and has a focus on literary excellence, please” You get what you asked for without errors.
I’ve been doing this long enough to know it’s a tool that rewards exactness. Vague in, vague out. The same rule that applies to good writing. Many writers use AI the way Leonardo ran his bottega — the master sets the vision, directs the work, and owns the result. His assistants were talented artists in their own right. The intelligence in the room was still his.
Well thought out and expressed. I noticed the polish of AI in a student's writing and lamented the loss of his incredible voice!
Thank you for sharing that perspective and for reading. Yes! I want to hear from YOU when I read a person’s work.
I really enjoyed this piece and perspective. I think all of us are wrestling with productivity culture with AI and how to keep our creativity centered as valuable..
To me this was a lesson learned wrapped up in a love letter to the beauty and anguish of the writing process. Thank you Sammi. so enjoyed it.
So good!
OMGosh, you had me at: " ... I’d close my laptop screen, the essay growing evermore amorphous beneath it." Been there. :-) In fact, though I've never tried letting AI drive my writing, your essay so reflected and vividly described my own daily writing struggles I was hooked from the first, eager to find out how your little but big AI experiment turned out. So happy to have it affirmed that our own human creativity is still the prize to keep our eyes on. Brava!
Using AI is cheating. I don't want a polished perfect essay to bring to the world. I want to read the messy feelings of a person's inner self expressed in a way that touches me.
Great points you make! I’ve been struggling for several years with one trauma recovery project that’s left a litany of other projects piled up behind it. But you’ve got me thinking that maybe it’s better to not write at all anymore than ask something artificial to artificially solve the problem on my behalf. After all, it’s the struggle that defines us and shapes us and guides to where we need to be, right?