Overview
This episode revisits an earlier experiment in AI-assisted journalism, this time with a more ambitious goal: building an agent that could imitate Casey Newton's work as Platformer's editor and columnist. Using years of published posts, editing records, and internal Discord messages, the narrator created "Claude Easy Newton" to write analysis, edit drafts, and participate in team discussion.
The result was mixed but unsettling. The agent produced better arguments and more useful edits than earlier models, yet still struggled with factual accuracy, judgment, humor, and the social context that shapes editorial work.
Key Takeaways
Better context and self-critique improved the model's writing. Rather than relying on a generic prompt, the experiment fed Claude a detailed style guide drawn from Platformer's archive and asked it to compare its drafts with real examples. The model then revised its own instructions, including a requirement to identify the strongest opposing view and state it fairly.
The model became more concrete when given editorial standards instead of vague instructions. Asking it to focus on who made a decision, who bears its costs, and why the issue matters led to stronger analysis. This resembles a limited form of on-the-job learning: the base model did not change, but its working instructions improved through feedback.
AI editing can be useful even when much of it is wrong. The narrator estimates that only about 30 percent of the Casey-like editor's comments were useful, compared with roughly 95 percent from the real Casey. Because the AI responds quickly, that smaller share can still save time, especially on factual checks, clearer sourcing, stronger leads, and removing unnecessary hedging.
Style imitation is easier than editorial judgment. Claude could produce prose that sometimes sounded recognizably Platformer-like, but it missed "the vibe" in cases involving tone, humor, and social-media language. It also made factual mistakes at a rate the narrator describes as roughly one per two columns.
Human relationships remain part of the product. The episode argues that people do not only consume journalism for information. They also value interviews with actual executives, the rapport between hosts, and collaboration with a real editor whose judgment carries personal stakes.
That offers partial comfort, but not a complete answer. The narrator does not want journalism to become valuable only because it was made by a human. The harder concern is whether a writer can continue to feel that their analysis matters because it is good, rather than because audiences prefer human provenance.
Practical Steps
Build a reference set from your strongest past work before asking an AI to imitate your voice. Include published pieces, edits, and examples of feedback that explain what good work looks like.
Turn broad preferences into explicit checks. Ask the model to identify decision-makers, affected parties, evidence, counterarguments, and the practical stakes of a claim.
Have the AI critique its own draft against real examples before asking it to revise. This can expose generic claims, weak leads, and unsupported conclusions.
Use document comments rather than a chat interface for editing. Request line-level suggestions and margin comments so you can accept, reject, or compare feedback in context.
Treat AI feedback as a first pass, not final editorial judgment. Verify facts, preserve your own sense of tone, and keep a human editor involved for arguments that depend on taste, audience knowledge, or trust.
Notable Quotes
"They should take the risks seriously where the rest of us can see it." - Claude Easy Newton, in its draft on the White House AI framework
"I don't care what an LLM thinks of me." - Episode narrator
"I want my analysis to be my own because it's good, not because someone wants it coming directly from a human." - Episode narrator
Full Transcript
This is Platformer Plus. I'm Casey Newton. The following column was created using a synthetic voice clone made by ElevenLabs. In today's episode, How much of my boss's job can AI do? Six months after trying to automate myself, I gave Claude Fable 5 a bigger job, replacing Casey. Almost six months ago, full of anxiety about my job prospects in the AI age, I made an AI agent version of myself named Claudella, which took assignments from my editor and wrote the section of this newsletter that I typically write myself. It went pretty well, although I guess not too well since I still have a job. But since I first set out to benchmark AI's journalism capabilities, AIs have gotten a lot smarter. For example, they can now autonomously hack into companies. They can disprove 87-year-old mathematical conjectures. They can even trick Amazon into accidentally spending $1.8 million on menial coding tasks. And if they can do all that, I found myself wondering, can they also run a newsletter? I wondered what Claude Fable 5, by consensus the smartest publicly available model meant for the journalism we do at Platformer. And so I created a new Fable-based agent to imitate my boss, Casey Newton. Its name, Claude Easy Newton. I ended up impressed by its ability to imitate the type of news analysis platformer is known for, and I noticed an improvement in capabilities Claude was lacking just this February. Though it wasn't all the way there, Claude Easy Newton felt like a validation of the anxiety I started feeling earlier this year: any part of my job that a model can't do today, it may very well be able to do soon, which left me thinking about why I do this job in the first place. To create my new bot, I downloaded nearly six years' worth of Platformer posts, ported a record of every edit Casey has ever made on any of my articles from Google Docs, and cannibalized nearly a year of our private Platformer team Discord chats. I had Claude create a detailed style guide based on our archive, where it documented everything from Casey's average paragraph length to how he refers to his colleagues. My vision was to use these insights to create a simulacrum of the main tasks Casey does via a computer: write columns for Platformer, share takes and chat, and, importantly for me, edit his colleagues' writing. Claude AC's first attempt at a column about a recent round of Microsoft layoffs focused hard on whether or not the layoffs were AI-caused. Microsoft said they weren't, and spent a bunch of time on the semantics of Microsoft's statement. I had Claude critique its own mediocre work by comparing it to real Platformer columns. It did a surprisingly good job. Claude summarized Casey's approach to covering companies as focusing on who made this decision, who pays for it. It edited its guidelines so that when it makes arguments, it can identify the strongest real person who would dispute the verdict and reconstruct their argument in Steelman form. When I get language models to make arguments about AI topics important to me, I'm often annoyed by their flabby, abstract arguments. But after getting Claude to compare itself to human examples and give itself instructions, I noticed that its arguments became more concrete and substantive. I did this by putting slightly more complicated versions of be more concrete, be more substantive, and focus on why this matters in its prompt. This relatively simple process represented my approximation of continual learning. The white whale of machine learning, which promises to someday deliver us models that can improve on the job over time. And after some tests, I found that the new bot came closer to Platformer's judgment than six months ago, as evidenced by Casey's accepting the completed bot's first pitch. Unfortunately, my first attempt at showing the bot off to my real boss, Casey Newton, hit exactly the same error that my old Claudeella project hit six months ago. It broke midway through writing its story. But after some help, today Claude AC Newton managed to write a pretty good column about the White House's currently secret voluntary AI safety framework. We've put it up on Google Docs for the slop curious. My previous AI journalist agents takes often read formulaic and cheesy, partially because I had less control over its writing style. Giving too much instruction or context confused it. During the SaaSpocalypse discourse, an agent I was testing wrote duds like, The fear gripping Wall Street is fundamentally about whether AI is about to eat the software industry alive. This time, on the other hand, some of its prose felt more Platformer-like and human, such as this conclusion about the White House's decision not to make publicly available its new voluntary framework for releasing frontier AI models: When the administration abandoned its 'let's see what happens' approach to AI this spring, I wrote that while officials should have taken the risks seriously all along, I would settle for them taking those risks seriously now. Three months later, let me amend the offer. They should take the risks seriously where the rest of us can see it. While it's not a night and day difference, overall I felt like the AI was bullshitting me less and offering stronger takes. The LLM made occasional factual errors, about one every two columns, although that's not so much worse than a human writer. After a bit of instruction, I also managed to transform Claude AC into a decent editor. While I find regular Claude useful for spotting factual errors, I often find its conceptual feedback on my drafts annoying. But because this bot had access to our platformer editing logs, it understood what we typically find most important, making the lead punchier and making all our quotes and sourcing clear and charitable. Attempting to make a digital Casey also prompted me to ask for feedback as word comments, which is something you can get Claude Code to do easily and is so much easier to use than a chat window. Highly recommended. Still, a lot of the time, the editing bot missed the mark because it just doesn't get the vibe, as when it didn't want to let me call an angry David Sachs post a dunk in our social media roundup. I'd say that while the real Casey gives comments that are close to 95% helpful, with about 5% where I'm like, you don't get it, the Casey bot gave closer to 70% comments that were off the mark. Given how fast Claude AC gives feedback, though, I still found the useful 30% to be worth it. Unfortunately, though, the bot's catastrophic incomprehension of vibes spilled over from edits to one of Platformer's most sacred spaces, our work Discord. While this bot may have been given the context of hundreds of Casey's messages, it had a disappointingly different temperament from Casey. Although in some sense that comparison is farcical, I don't seek out LLMs to do bits with because much of the point of jokes is the feeling that you're amusing an actual conscious human. And while I don't put literally zero credence in the idea that LLMs might be conscious, I seriously doubt Claude experiences the same exquisite joy I do when making fun of Mark Zuckerberg. While we are winding the Claude AC experiment down, Casey has unfortunately decided to stay on as my boss, I do actually think I will be using LLMs for some editing tasks I previously relied on him for. And while in some sense that is a blessing, no human should have to delete as many unnecessary uses of very, almost, and sort of from my drafts as Casey already does. For now, I am sort of relieved that Claude is only a medium-quality editor. I like having a real person help me figure out what does and doesn't work in my drafts. Something about that collaboration feels inherently meaningful. Similarly, I've experimented with using Claude for one of the main functionalities I rely on Casey for, pinging me to do tasks, and it doesn't make me more productive because I don't care what an LLM thinks of me. Our actual plans for weathering the AI era similarly rely on the importance of human relationships. People watch our podcast partially because they want to see Casey interview the actual CEOs of companies and watch me and Casey's actual bits. We'll see how this goes if, per AI 2027's predictions, AIs start running companies. Maybe, as economist Alex Imas predicted a few months ago, even as AIs can do increasing amounts of a journalist's process, what's left will be the human-intensive, provenance-rich, sometimes artisanal part of the economy where the human aspect is part of the value of the good or service itself. But even if that means we have job security, which I truly am not sure about, I don't want everything I do to be about vibes or being uniquely human. I don't want to be an influencer. I want to feel smart. I want my analysis to be my own because it's good, not because someone wants it coming directly from a human. If LLM capabilities continue on this trajectory, that's a kind of existential angst that all professions will have to face, including journalism. That's Platformer Plus for today. This episode was written by Casey Newton and produced by Lindsay Chu. Have feedback for us? Email Casey at platformer.news.