“Claude Opus 4.1, De-Carcinize the Great Gatsby” (That was the only prompt)
Pretty clever, actually.
# The Great Gatsby: De-Carcinized
## Chapter 1: Direct Approach
Nick Carraway moved to West Egg and immediately walked straight to his neighbor Jay Gatsby’s house.
“Hello,” Nick said. “I’m your new neighbor. I notice you throw parties.”
“Yes,” Gatsby replied, opening the door fully instead of peering through a crack. “I throw them hoping Daisy Buchanan will attend. She lives across the bay. I love her.”
“She’s my cousin,” Nick said. “She’s married to Tom.”
“I know. Would you arrange a meeting?”
“Sure.”
## Chapter 2: Honest Communications
Tom Buchanan stood in his living room, addressing everyone directly. “I’m having an affair with Myrtle Wilson. Daisy, you probably know this. Myrtle, you should know I’ll never leave Daisy for you.”
Myrtle nodded. “I understand but choose to continue anyway.”
Daisy turned to face them. “I’m unhappy but too comfortable to change anything.”
## Chapter 3: The Party Without Pretense
Gatsby’s next party featured a sign at the entrance: “These Parties Are Specifically to Attract Daisy Buchanan’s Attention.”
Guests arrived and immediately stated their intentions:
“I’m here for free champagne.”
“I’m networking for business.”
“I enjoy judging rich people.”
Gatsby stood on a platform with a megaphone: “Thank you all for coming to my Daisy-attraction event. Please enjoy yourselves while I wait hopefully by the window.”
## Chapter 4: Swimming Forward
Gatsby drove Nick directly to the city—no detours through the Valley of Ashes, no sideways routes through East Egg.
“I should tell you my backstory without any embellishment,” Gatsby said. “I was born poor as James Gatz. I made my fortune through questionable means with Meyer Wolfsheim. Everything I’ve built is to win Daisy back.”
“That seems unhealthy,” Nick observed.
“It absolutely is,” Gatsby agreed.
## Chapter 5: The Reunion
At Nick’s house, Gatsby walked straight to Daisy when she arrived.
“I’ve loved you for five years,” he said. “I’ve built my entire life around the hope of resuming our relationship.”
“That’s concerning,” Daisy replied. “But I’m flattered and bored in my marriage, so let’s proceed.”
They looked at each other directly, no dancing around the truth.
“This will end badly,” they said in unison.
“Want to see my house?” Gatsby asked.
“Yes, though material possessions won’t fix our fundamental incompatibility.”
## Chapter 6: Clear Waters
Tom attended Gatsby’s party and immediately announced: “I distrust you and will investigate your background.”
“Fair enough,” Gatsby replied. “I am indeed hiding things.”
Daisy pulled Gatsby aside. “These parties make me uncomfortable. You’re not the same person I loved five years ago.”
“You’re right,” Gatsby admitted. “But I’m unable to accept that.”
## Chapter 7: Direct Confrontation
In the hotel room, everyone laid their cards on the table—literally, they brought actual cards with their feelings written on them.
Tom’s card: “Gatsby is a criminal.”
Gatsby’s card: “Daisy loves me, not you.”
Daisy’s card: “I love security and comfort more than either of you.”
Nick’s card: “I’m uncomfortable and want to leave.”
Jordan’s card: “This is entertaining.”
“Well,” Tom said, “since Daisy has clarified her priorities, and I offer more security, I win.”
Gatsby nodded sadly. “Your logic is sound.”
## Chapter 8: Forward Motion
Driving home, Daisy didn’t swerve or panic. She drove straight and responsibly, arriving home without incident.
“That was anticlimactic,” Gatsby said.
Later, Wilson approached Gatsby at his pool.
“Did you have an affair with my wife?” Wilson asked directly.
“No, that was Tom Buchanan. He just told you it was me to deflect blame.”
“Oh. My mistake.” Wilson left to find Tom.
## Chapter 9: The End Without Shells
Gatsby, still alive, realized his obsession was unhealthy. He sold his house and moved to California to start fresh.
Nick wrote in his journal: “Today I learned that approaching life directly, without sideways scuttling or defensive shells, leads to less tragedy but also less poetry. The green light across the bay was just a light. The eyes of Dr. T.J. Eckleburg were just an advertisement. And we all moved forward, not backward, walking upright instead of sideways, exposed but honest.”
Tom and Daisy stayed married, openly acknowledging their mutual dysfunction.
Myrtle left Wilson and opened a successful boutique.
Jordan became a professional golfer who actually followed the rules.
And Nick? Nick went back to the Midwest immediately instead of lingering to narrate everyone else’s drama.
## Epilogue
So we beat on, boats moving directly forward with the current, making excellent time to our clearly stated destinations, no longer crushed by the weight of our own protective shells or the insistence on moving sideways when forward was always an option.
*The End*
-----
*Author’s Note: In this de-carcinized version, all characters have shed their protective shells of pretense, ceased their sideways approaches to truth, and emerged from the murky bottom-feeding of their social world. Without their crab-like qualities, they resolve conflicts with unsettling efficiency, proving that sometimes evolution’s mistakes make for better literature.*
This is, in fact, what early acceleration of science looks like with jagged AI.
Writing abstracts takes a lot of time, many scientists are bad writers and clearly written abstracts are important. As long as the authors check over the results, this is a good use case for AI.
We do not yet have true autonomous science or breakthrough ideas from AI, but AI provides time savings throughout the process when used carefully by humans: data cleaning, exploratory analysis, writing, pushing back on ideas, (deep) research - all can be helpful when used well.
Kinda amazing: the mystery model "summit" with the prompt "create something I can paste into p5js that will startle me with its cleverness in creating something that invokes the control panel of a starship in the distant future" & "make it better"
This is through LMArena, where you are given random models to test. You will likely get a chance to use "Summit" fairly often (it came up three times in my six attempts): lmarena.ai
They are often far worse at getting AI to do stuff than those with a liberal arts or social science bent. LLMs are built from the vast corpus human expression, and knowing the history & obscure corners of human works lets you do far more with AI
These are systems that respond to human writing and (often) techniques that apply to human psychology.
Everyone now has a machine that makes words, images, video, sound where the limit is often your own ability to imagine something new (or invoke old ideas others do not know).
The Math Olympiad is great, coding is important, accelerating science has tremendous value.
But LLMs give a chance for both cultures to contribute in ways that have not been possible for a long time.
X (and other social media sites) make our 1990s optimism about the Information Age seem silly.
Even with all of the world's information a click away (& a free AI that can help explain that information in a personalized way), half-mangled anecdotes with no source win every time.
It really is not what most people who was working on building the early web in the late 1990s were expecting. Universal access to information was going to transform everything, creating widespread learning and bridging divides.
It really is shocking how much that didn't happen.
The fact that people use the internet mostly for entertainment isn't a weird or surprising
But you also have access to courses on every topic by experts, every major out-of-copyright book, can talk to people from anywhere, etc. The impact of that is smaller than I once expected.
So, OpenAI Deep Research can connect directly to Dropbox, Sharepoint, etc.
Early experiments only, but it feels like what every "talk to our documents" RAG system has been aiming for, but with o3 smarts and easy use. I haven't done robust testing yet, but very impressive so far.
I think it is going to be a shock to the market, since "talk to our documents" is one of the most popular implementations of AI in large organizations, and this version seems to work quite well and costs very little.
I am sure the other Deep Research products will be able to do the same soon, and, while I am sure there are hallucinations (haven't spotted any yet, though), this seems like an example of how the LLM makers can sometimes move upstream to the application space and take a market.