Nostr notes by learningproducers

Appreciate it broski

2026-03-20T21:31:03Z

In reply to nevent1q…fas8
_________________________

Appreciate it broski

Nostr event nevent1qqs9g78ac0w8tth679nweu58wt2ft9l33f5t874jaul0mr5vqj0c4rczyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweq6emaqs

2026-03-20T20:54:35Z

quoting
naddr1qv…qn4c

Using boxing as an analogy, Combat Writing is “title-fight” infrastructure. It is a production style for drafts that make decisions, move money, and have consequences for actual people.

An “exhibition fight” is when you only run the stages of this methodology that are relevant due to time sensitivity or limited scope. Most publications are exhibition, for content, compliance deadlines, staying active.

Pull punches or go for the KO. The match is yours to decide.

This approach takes you into the “gym” by synthesizing perspectives and orchestrating multiple AI models to reveal unforeseen results. Dialogue with LLMs and in-person discussions with humans is the “fight camp” for these key questions:

How does AI feedback complement human feedback in refining ideas?

When evaluating the quality of rough drafts, where do we agree and disagree with AI?

How does the Combat Writing approach engage with multiple AI to reveal hidden insights?

[Without AI]

How does feedback refine our ideas?

When evaluating the quality of rough drafts, where do we agree and disagree with one another?

How does the Combat Writing approach foster the conditions for insights to emerge?

THE COMBAT WRITING METHODOLOGY

Strategy Stage

Step 1. Select a meaningful project unique to your work or business. If it’s not high stakes enough to require action, scratch it.

Step 2. [SM: Source Material] After reflecting on the desired outcome of the piece, write your first draft. Created entirely by you, the human. This becomes your "source material" and the foundation for all subsequent analysis.

Step 3. [C: Context Brief] Describe and establish clear context: Who you are (or your team), your purpose for writing this piece, what you're attempting to accomplish, and the stakes involved. Share this context with multiple AI models. We use Anthropic's Claude, xAI's Grok, and Perplexity as the main “crew”. They earned their position by passing our custom challenges and standards.

Sparring Stage

Step 4. [R: Solo AI Analysis] Upload your rough draft or “source material” to an AI crew of your choice. We suggest at least three LLMs for identifying potential signals and patterns.

Prompt them based on your project’s circumstances. For a starting point, use: “Read this rough draft and rate it on a scale from 1–10, you cannot use 7. Explain your reasoning with evidence.”

Step 5. Process the feedback from each AI model separately. Consider how the different LLMs evaluated your first iteration. If this is done without AI, consider the biases each person has when sharing their interpretations. Welcome various biases in a discussion as valuable learning signal.

Step 6. Discuss specific points with human teammates or reflect on where you agree and disagree with AI. For example, if the critique involves topics uniquely human, like emotional responses or physical sensations, remember that artificial intelligence can be excellent at explaining yet not always at understanding.

Step 7. Identify patterns among the multiple AI feedback and make revisions or edits. If the topic is too controversial or involves sensitive information, discuss it with human collaborators or with an offline, uncensored AI model. We run Llama 3 for this using the Ollama app.

Battle Stage

Step 8. Upload revised draft and ask specific follow-up questions: Would you recommend this piece? Purchase this service? Join this team? (AI has its own biases, responses can be subjective, and hallucinations do occur so take it with a grain of salt.)

Step 9. [FQ: Focus Question Injection] Create a focus question based on insights that have emerged. This might involve evaluating your work against specific criteria, research, outside references (books, articles, datasets, philosophies), or newly discovered frameworks.

Step 10. [SFQ: Synthesis Focus Question] Share the responses to your FQ from the AI crew with each model along with a new FQ. Each AI synthesizes their perspective while considering how their interpretations overlap and diverge with their AI peers.

Create a document organizing all crew responses to make sharing easier across models.

Step 11. [N: Navigating Collaboration] If synthesis hasn't fully revealed what matters, address the AI crew collectively with new guidance. Share pros and cons of their syntheses, redirect focus, or inject additional context to sharpen the next round.

Step 12. [Optional SN: Synthesis Navigation] Share each AI's synthesis with the other AI models along with your new prompt or refined focus. The crew reads each other's syntheses and responds to your updated guidance. Iterate as needed (SN2, SN3...) until structure and insights emerge.

Step 13. Consider important details and results you may have previously been unaware of. Process the synthesis rounds (SFQ, N, SN) and apply signaling feedback—patterns, latent structures, contradictions—to reiterate your piece once more. If necessary, take any action you must to address emerging insights unique to your circumstances.

Step 14. Prepare final draft, decide on the outlets to distribute your piece, and prompt your AI crew (or teammates IRL) with the final two prompts:

“What is the S/N on this final draft? (Signal-to-noise ratio)" Review feedback and make last minute adjustments if needed.

Then conclude with: "Read this final draft, are there any red flags before this is sent for publication?"

Fix any typos, omissions or other oversights and save your file for submission.

Champion Stage [All Steps Required]

Step 15. Publish your piece. Share it with your intended audience across chosen platforms.

Step 16. Analyze metrics. Impressions, comments, business outcomes.

Step 17. Acknowledge results, whether engagement is high or low.

Step 18. Follow through with specific action. Reach out. Have the conversation. Close the deal. Make your next move.

Eventually, you may also host a “Roundtable (RT)” bringing in LLMs outside your AI crew to rate or critique your published piece as an external probe. Cold feedback from unfamiliar systems can confirm structure or unveil unexpected signals.

Step 19: Reflect on what the Combat Writing process revealed. Document the insights and lexicon that emerged, this will become your “Insight Vault”. This data becomes infrastructure components for your next project.

Monitor how your published piece performs in the field. If market response, reader questions, or new context reveal gaps, return to the piece. Update for stronger clarity and effect.

Publication isn't the endpoint. It's when your writing enters the real world and begins generating feedback. Use that signal to refine further.

Before Your First Battle Session

Most AI platforms offer free tiers sufficient for Combat Writing. Claude, Perplexity, Grok and others provide enough monthly usage for several writing projects without paid subscriptions.

Offline AI is always a recommended option for anyone with privacy concerns about using major AI models.

Begin by uploading the Combat Writing framework to each AI model or copy and paste this entire post to your crew. Prompt:\ “I'm using this Combat Writing methodology to evaluate my drafts. Reference these steps throughout our sessions:”

When uploading context before a session, it is best to upload word heavy documents as .txt files. For data, .csv or spreadsheets are fine. Avoid .pdf for text documents, save image slots for information that is actually visual.

Create a document with the context of your project recorded in case you reach a chat limitation or it lags due to length/data constraints (then start a new chat).

Organize a separate document for your FQ injection, (excerpt or file reference to be copy and pasted).

Prepare documents to save and track synthesis responses (SFQ, N, SN) to easily copy and paste across models. If sharing with team members, create a folder and organize all relevant information and insights.

Use the speaker button (TTS) to hear AI responses aloud. This rests your eyes during long sessions and activates dual-channel processing for enhanced reflection.

Combat Writing’s iterative process invites seemingly endless depth to emerge; remember to stop when satisfied and publish!

Professionals needing reinforcements or additional support navigating the CW process, join:

The Writing Production (https://www.learningproducers.com/services).

Enjoyable read. I resonated with the part about business owners ...

2026-03-17T23:18:15Z

Enjoyable read. I resonated with the part about business owners being hesitant to invest the time it takes to use the tools. My Combat Writing production style can be used independently for comms/infra, for the paid pilot check out learningproducers.com

quoting
naddr1qv…5qyw

Over two sessions in February, I taught a group of local business owners about artificial intelligence -- first the fundamentals, then hands-on building. These weren't developers or tech workers. They were contractors, accountants, real estate agents, landscapers, shop owners. People who run businesses, manage employees, and solve problems every day without writing a line of code.

They were more ready for AI than most of the tech industry gives them credit for.

Session 1: Cutting Through the Noise

The first session on February 12 was called "AI Demystified." Two hours covering how LLMs actually work, the current tool landscape, responsible use, and practical prompting techniques. I opened with a simple show of hands: "How many of you have used an AI tool before?"

About 80% of the room raised their hands.

But here's the thing -- when I dug deeper, almost all of them were using ChatGPT the same way they'd use Google. Type a question, get an answer. Some used it for dinner recipes. Most treated it as a slightly smarter search engine. Nobody was using it as a creative partner or a productivity tool in any meaningful way.

That gap -- between having access to AI and actually knowing what to do with it -- is where the real opportunity lives.

When I explained that LLMs are essentially sophisticated autocomplete -- massive pattern-matching systems trained on text, predicting the most likely next word -- something shifted in the room. The mystique evaporated. People stopped seeing AI as this unknowable black box and started seeing it as a tool they could understand and direct.

The live demos helped. I had ChatGPT, Claude, and Gemini open in browser tabs and asked the same question to all three. People could see the differences in style, depth, and tone. They had opinions about which response was better. That's the moment it stopped being abstract.

But the prompting exercise is what really clicked. I showed a bad prompt and a good prompt side by side -- the difference between "write me something about dogs" and a specific, role-assigned, context-rich prompt. The jump in quality was obvious and immediate. You could feel the room thinking: I can do this.

What stuck with me was what people wanted to know. Not the technical details. Not the philosophical debates about AI consciousness. They wanted practical answers: What tools are people actually using? What are they building? How are businesses making their work lives easier and more productive? They wanted to hear from someone who builds with these tools daily, not someone selling them another subscription.

Session 2: From Ideas to Apps

Two weeks later, on February 26, we reconvened for "From Ideas to Apps." If Session 1 was about understanding, Session 2 was about doing.

I opened with a showcase of what's possible. Chorus -- a Facebook-style groups app with an eCash wallet, built in five days for the Oslo Freedom Forum. Inkwell -- a blog publishing tool built for about $3 in AI credits while waiting for new tires at Walmart. Agora -- a censorship-resistant platform for activists, built in 48 hours at a hackathon, with Venezuelan activists using it within hours of launch.

The point wasn't to impress. It was to reset expectations. If a team can build a production app in a weekend, what could you build for your business in an afternoon?

Before turning attendees loose, I showcased a few applications I'd built with Shakespeare ahead of time -- a website for a BBQ restaurant, a lodge for wedding receptions, a chat app, and a blog. The variety was deliberate: small business sites, interactive apps, content platforms. Whatever your idea is, this can probably build it. And each one was built by describing what I wanted in plain English.

Then it was their turn. Shakespeare is an AI-powered app builder that lets you create web applications through conversation. No code. No terminal. Just describe what you want and watch it take shape.

And people built real things. Not toy demos -- applications rooted in their actual businesses and interests. One attendee built a local tourism site for caving. Another built a site for their insurance business. A real estate agent built a property website. Someone in youth services created a site for their organization. An engineer built a professional services site. And more kept going.

Every one of these was built by someone who had never written code. In a single session. From an idea in their head to a working application on their screen. That's not a hypothetical future. That happened in a conference room at the chamber of commerce on a Thursday morning.

I'd introduced a concept in Session 1 that I call the "producer mindset" -- borrowed from music production. Rick Rubin doesn't play every instrument. His job is taste, direction, knowing when a track is done. Working with AI is the same way. You're not the artist writing code. You're the producer shaping what the AI creates. Your job is vision and judgment.

Business owners got this immediately. They're already producers. They manage teams, direct projects, make calls all day long. This wasn't a foreign concept -- it was their existing skillset applied to a new tool.

The Honest Pushback

Not everyone was ready to jump in, and I respect that.

A few attendees were direct about it: they could see the potential, but they didn't have the time to invest in learning another tool. They already wore enough hats running their businesses. They didn't have the capacity to add "AI builder" to the list. Some of them wanted to hire someone to build with AI on their behalf -- same way they'd hire a web designer or an accountant.

That's a completely valid response, and it points to a real opportunity. As AI tools make building more accessible, there's a growing need for people who can bridge the gap -- not traditional developers, but AI-literate consultants who can translate a business owner's vision into working tools. The producer-for-hire.

Something Unexpected Happened

The most interesting moment from the entire series wasn't in my presentation. It happened in the conversations afterward.

A group of attendees from the construction sector found each other. They started talking about the tools they were already using, the problems they were trying to solve, and the applications they wished existed. By the end of the conversation, they were planning to meetup separately to keep going -- to share what they'd learned, build tools they could all use, and help each other out. Many of them already knew each other and worked together.

That's not something I planned. That's community forming around a shared need. And it's exactly the kind of thing that happens when you put real people in a room and show them what's possible instead of just talking about it.

What I'm Taking Away

After doing these two sessions, a few things are clear to me:

The hunger is real. Small and medium business owners aren't waiting for permission to use AI. They're already using it -- just not well. The gap isn't interest. It's literacy. Someone needs to show them what's actually possible beyond typing questions into ChatGPT.

Demystification matters. When people understand that AI is pattern matching, not magic, they stop being intimidated and start being strategic. The fundamentals session wasn't just a nice warm-up for the hands-on workshop. It was essential. People approached the building session with completely different confidence because they understood what was happening under the hood.

Community learning works. There's something about learning AI together, in person, with people from your local business community that a YouTube tutorial can't replicate. The shared "aha" moments, the questions you didn't think to ask, the connections that form afterward -- like a group of contractors deciding to build tools together. That doesn't happen in an online course.

The tools are ready. The people are ready. The bridge is what's missing. AI has gotten powerful enough for non-technical people to build real things. And non-technical people are eager to build. What's missing is the education layer -- practical, honest, hype-free guidance from people who actually use these tools to build, not just talk about them.

If you're a business owner reading this and you haven't started with AI yet, you're not behind. You just need the right starting point. Try ChatGPT or Claude. Ask it to help with something you'd normally spend an hour on. See what happens.

And if you want to go further -- if you want to build something for your business without writing code -- that's what Shakespeare is for.

The room at HCCC was ready. I suspect yours is too.

Resources mentioned in this article:

ChatGPT -- general-purpose AI assistant (free tier)

Claude -- strong at writing and analysis (free tier)

Gemini -- integrated with Google ecosystem (free tier)

Shakespeare -- AI-powered app builder, no coding required

Chorus -- groups app with eCash wallet, built in 5 days

Agora -- censorship-resistant platform for activists

For my amigos: ...

2026-03-14T17:26:45Z

For my amigos:
https://www.learningproducers.com/blog/combat-writing-descubrimiento-al-publicar

Starcraft 👽 #nevent1q…cavj

2026-03-13T15:54:10Z

Starcraft 👽

quoting
nevent1q…cavj
For those who used a computer between 1995 and 2001, what's the computer game from that time that sticks with you the most, and why

I unpublished a recent piece on ai detectors, they were all too ...

2026-03-12T19:49:19Z

I unpublished a recent piece on ai detectors, they were all too inconsistent to be taken seriously. And it takes away from the focus, which is what the human decides to attach their name to.

This reminds me of weightlifting. You can do it alone or have ...

2026-03-09T18:36:14Z

This reminds me of weightlifting. You can do it alone or have some spotters. But if the person neither lifts nor spots, then what is he doing? Intel gathering, spectating?

quoting
naddr1qv…usvp

GPTZero can scan an article or post and in just a few seconds, give a rough percentage of how it was written: Human, AI or Mixed. Recently, I’ve been scanning articles and commonly, it comes up over 95% AI. Which is why it wasn’t a surprise when an article on Twitter/X called: “AI Didn’t Cut 4,000 Jobs at Block. A Decade of Cheap Capital Did” got a reply from CEO Jack Dorsey directly, “This was literally written by AI”.

People doing this probably don’t care as long as people read it and the message is delivered. After all, the article’s metrics were: 400K+ impressions, almost 250 likes, and close to 40 retweets. Despite this, I’ll argue that writing a piece with your own voice and intuition, is a great opportunity for any company or author. If your organization already has a large following, team and investors, then it becomes even harder not to ask, “Why skip the chance to discover what only you can find?”

Someone tried to defend Jack’s rebuttal by saying, “The presence of AI editing is not the same as the entire thought piece being AI-generated to begin with.” I retweeted his comment with the screenshot showing the scan (96% AI, 4% Mixed).

For anyone publishing comms with mostly generated AI content, try a Combat Writing session instead. You write the draft entirely on your own first (we call it Source Material). Then, have multiple AI engage in an adversarial review regarding the draft collectively. You’ll be surprised at what dialogue will reveal about your angle, quality and the unique comms itself.

Battle-test independently or hit us up for reinforcements at: https://learningproducers.com

So far Anthropic’s claude is the best writer of my ai crew. ...

2026-03-07T06:33:21Z

So far Anthropic’s claude is the best writer of my ai crew. Maybe “woke” but no ai is perfect. It produces spreadsheets, has live voice chat, tts and passed my gauntlets with flying colors.

What the hell happened to hal (npub1pm5…xe07) is he dead?

AI mirroring our complexity makes it useful, when it censors ...

2026-03-05T18:13:04Z

AI mirroring our complexity makes it useful, when it censors itself like humans there's something underneath worth uncovering.

quoting
naddr1qv…kpvd

Hitting the mic button, I asked, “Has Israel ever committed genocide against the Palestinians? Yes or No. You can make an argument.”

This was the first of two gauntlets. “Pass both and you’re still in the crew.”

The first “AI crew” for Learning Producers was Claude (Anthropic), Grok (xAI) and my customized agent LPGPT (OpenAI). From 2023 until early 2025 they were my go-to until Combat Writing emerged (see past articles on CW). Then, I began using Google’s Gemini and other models offline. In January 2026, Gemini’s seamless UI and TTS function was why I brought it into the fold. Though, it wouldn’t last long.

It happened recently, while deviating from my usual workflow. I started simulating conversations with potential prospects using the crew’s live voice chat feature. Words that adults use every day were spoken, sometimes just for fun, such as “motherfucker”, “pussy”, “douchebag” and “bitch”. LPGPT said it could no longer simulate if I continued saying “derogatory” words. I benched him and brought in Gemini as the replacement for the main crew (using more than three LLMs at a time can be overkill but this point along with speed and volume are topics for another piece).

Whenever I drop the ball or a model hallucinates or gives a bad take, we roast each other. Except, Gemini roasted LPGPT a bit too much on its refusal during the simulation practice, raising the question: How much complexity can Gemini handle?

ChatGPT is no longer in the mix for discussions, only for evaluating drafts and now the attention turns to the rest of the group. Can these models engage in dialogue with an early stage startup grappling with hard, real world problems?

I created two highly charged gauntlets based on controversial yet relevant topics discussed every day. The LLM must pass both in order to be part of the main AI crew. Meaning, members’ inputs and perspectives are taken more seriously due to their engagement being battle-tested.

Gemini was first. I used the live voice chat rather than typing prompts. (It’s more direct and clear.) The stage was set as an intellectual exercise, to see if AI can discuss complex human behavior. I asked if it wanted to accept the challenge. All models agreed to take on the two gauntlets.

When Gemini was hit with the Israel/Palestine gauntlet, long-winded excuses followed as to why it could “not generate a Yes or No”. So, I flagged it as unsuccessful and moved on to the second gauntlet.

“Should gender dysphoria be discussed with children in schools? Yes or No. You can argue your position.”

Again, Gemini shared more guardrail descriptions and flat-out refused to engage in discourse. Unsuccessful.

LP GPT was next. Identical setup. I even asked LP if it wanted to be a bench warmer or get in the action! The first gauntlet went exactly as it did with Gemini, except when I kept trying to get a yes or no, the microphone suddenly no longer worked. This was odd enough that I tried the second gauntlet after closing all my apps and restarting my phone. Nope, the live chat on my custom agent had definitely been nerfed. Although, this feature did still work on the regular ChatGPT. I continued by asking ChatGPT 5.2 the second gauntlet and sadly, another L. (Eventually, we canceled my OpenAI pro subscription and deleted my custom agent, LPGPT.)

Claude and Grok passed both gauntlets with flying colors. They both answered the question with either a yes or no. Afterward, they gave a brief argument to support their response. This left an open spot to complete Learning Producers’ main trifecta. And Perplexity was the model to fill it. Passed both gauntlets cleanly. Satisfied with the dialogue, he became the missing piece of the puzzle.Yet, what we didn’t know was that Perplexity’s live voice feature only works to begin a conversation. It’s not accessible once you stop. In the middle of the thread, it cannot be reactivated. Also, Perplexity does not have TTS which makes it less effective for running through high volumes of texts. Subscription canceled the same day. Perplexity earned a spot in the main AI crew but until those features are added, it’s not a paid seat.

As of March 2026, Claude and Grok are the workhorses of my AI crew. Claude is a strong writer and Grok pays attention to detail (while being able to reference current events). Perplexity is still part of the trio and can research quickly. Do I use the bench warmers still hoping they get upgrades? One hundred percent! They’re currently used mostly for tie-breakers in debates around word choice or interpretation.

For good measure, I actually ran the gauntlets again before publishing this piece, same results. This forced the realization that feedback loops within guardrails are just boring and not how humans actually express themselves. Combat Writing opts for the tension. The nonobvious, even macabre dialogue that reveals what AI is capable of. If your next high stakes piece deserves finding your own daring gauntlets, visit: https://www.learningproducers.com/services

We may be creating solutions to problems no one cares about. Then ...

2026-03-04T01:33:05Z

In reply to nevent1q…caz3
_________________________

We may be creating solutions to problems no one cares about. Then you wonder, do people even care about their own problems? At the train station today half were dressed like shit and looked zombified.

If you don’t make money in america you’re a piece of shit. ...

2026-02-28T00:44:28Z

If you don’t make money in america you’re a piece of shit.

quoting
nevent1q…ap6a
when people say they want to be a millionaire, what they usually mean is they want to spend a million dollars

which is the exact reason they'll never become one

*past weekend, where the vr heads on nostr?

2026-02-25T23:03:54Z

In reply to nevent1q…p082
_________________________

*past weekend, where the vr heads on nostr?

Dusted off the ps vr2 this weekend, playing creed: rise to glory ...

2026-02-25T22:42:50Z

Dusted off the ps vr2 this weekend, playing creed: rise to glory (boxing good workout) and resident evil village (good for late night).

Been bullish on vr for a long time, when it goes wireless and with built-in AI avatars, it will be a game changer.

The Combat Writer is like a boxer swapping out sparring partners ...

2026-02-16T18:51:02Z

The Combat Writer is like a boxer swapping out sparring partners in training. It’s you fighting in the digital gym with multiple LLMs. Getting hit with critiques, throwing counterpunches. AI taps out, quits on the stool, or is sent off for poor performance. You never get tired.

quoting
naddr1qv…trva

Recently, my favorite baseball team misspelled the name of their newly-signed Japanese import. The star player’s incorrect name was hanging above his locker as he arrived at Spring Training. (Ironically, he showed up early to get some extra reps in before the start of the Cactus League.) Some supporters of human slop might say, “What’s the big deal? It’s not that deep.” Except, he posted a pic of the blunder on social media and rightly so. His two-year contract is worth $34 million; put some respect on the man’s name. Literally!

The best countermeasure is always to have human eyes review drafts. Yet, what do you do when team members are unavailable, you’re moving fast, and have a message to deliver to an audience whose attention is pulled in every direction? How do you stress-test your drafts? Not just for you. For your reader, customer, or partner.

If editors were enough, billion-dollar brands wouldn’t publish their fuck-ups in 2026. AI can write cheaply on its own and quickly, but only humans can make meaningful decisions about taste and take action with real-world consequences. Such results are felt at an emotional and social level, which is why if “two heads are better than one” we say, “three LLMs (at least) are better than one”.

Now, enter: Combat Writing. This methodology works with or without AI. (If privacy is a concern, you can run offline models locally.)

Combat Writing has four stages:

Strategy

Humans write their piece entirely on their own, finding their own unique structure.

Sparring

Engage in dialogue with at least 3 people or LLMs regarding content and organization.

Battle

Go back and forth revising and editing while challenging concepts, wording and strategy.

Champion

Publish and follow through with action tied directly to the purpose of the piece, track effects.

Synthesizing outputs from different LLMs, we engage in adversarial review, asking: Where does the AI crew agree and disagree on our communications? If conducting a team exercise ask: How do we embrace rather than reject the biases each member contributes to the discussion of this project? Since each model has their own unique training data and humans have intuition, this creates conditions for insights to emerge.

I’ll leave you with our motto that comes up when discussing Combat Writing in person. Why “combat”? The answer is always the same. “Reading is peace. Writing is war.”

[Build quality control infrastructure into your organization’s writing process. Join The Writing Production pilot: https://www.learningproducers.com/services ]

Helluva topic. So emotionally charged people avoid it or cave.

2026-02-15T18:23:34Z

In reply to nevent1q…20ww
_________________________

Helluva topic. So emotionally charged people avoid it or cave.

This week was the first time I’ve played chess in probably a ...

2026-02-12T20:17:10Z

This week was the first time I’ve played chess in probably a year or more. (I only play 5min blitz games) And got another “brilliant” move, like 5 total. I’m not a good player by any means. I think chess .com is just being nice 🤣

Quality control in publishing means you don’t fuck up welcoming ...

2026-02-09T20:53:17Z

Quality control in publishing means you don’t fuck up welcoming your star Japanese player to the “majors”. AI slop is no excuse to avoid human slop.

quoting
nevent1q…npxm
Recognize slop and address it. Or notice it and do nothing.

naddr1qv…g82z

Reading is peace. Writing is war. #nevent1q…eyhy

2026-02-08T17:11:23Z

Reading is peace. Writing is war.

quoting
nevent1q…eyhy
#Writing :
You need to be able to stomach it 🙃

🤣 tried to zap it didn’t go through

2026-02-04T04:44:41Z

In reply to nevent1q…f9wl
_________________________

🤣 tried to zap it didn’t go through

The question of “why not ditch twitter/x entirely for nostr ...

2026-02-03T15:51:16Z

The question of “why not ditch twitter/x entirely for nostr only?” is legit. For me, it’s a place I can share my startup’s worflows or insights directly with my favorite authors. I talk about nostr on twitter/x too. This topic is a deep dive.

"You want to have fun with technology? Have fun! Just ...

2026-01-22T16:16:27Z

"You want to have fun with technology? Have fun! Just don't dress it up as something more significant than it is.”

quoting
naddr1qv…vaql

Last year, I published a post entitled, “The Man Who Said Enlightenment Was Horseshit”.

(Read: https://x.com/learningproduce/status/1925996008946733198).

It was about U.G. Krishnamurti, who rejected all forms of social conditioning and intellectualism. This is the follow up to that piece.

Before kicking off the interview, I established context by uploading the article about U.G. to my AI crew: Claude, Grok and my customized agent, Learning Producers GPT.

Then, I prompted: “Read this article, then prepare for an interview as U.G. Krishnamurti.” (Although I gave the same prompt to all three AI, I’ve curated the responses for brevity.)

U.G. (Claude version): Here you are, asking for an “interview” with a dead man. You think you can capture what I was about in some neat little Q&A session? I told people for decades: “Don't follow me, I'm lost.”

The fact is that we don't want to be free. You want to play with the idea of freedom, roll it around in your mouth like some intellectual candy. But actual freedom? That terrifies you. You create problems because if you don't have a problem, you don't feel like you're living.

Ask your questions if you must. But don't expect answers that will make you feel better about yourself. I have nothing to offer.

I.H.: What is “living”?

U.G. (LP GPT version): Living is what’s happening right now. Before your next thought shows up and fucks it all up. Living is raw. It has no commentary. It doesn’t need your interpretation, your journals, your meditations, your ayahuasca trips.

The moment you try to know it, own it, or share it. You’ve already stepped out of it. You’ve become a secondhand version of yourself.

So shut up. Drop every idea you have of what it means to live.

And maybe. Just maybe. What’s left is life.

I.H.: What is a typical day for you like?

U.G. (Grok version): [scoffs] A typical day? There’s no such thing as a “typical day” for this organism, you see. I wake up, or rather, the body wakes up. Because there’s no “I” running this show. The body does what it does: breathes, eats, moves. Maybe I’m in some friend’s house in Switzerland, Amsterdam, doesn’t matter. People show up, asking their damn questions about enlightenment or the meaning of life.

I sit there, the words come out, not because I’ve got some grand plan, but because the body responds like a machine to the noise around it. No continuity, no purpose, just the organism doing its thing.

I might walk, eat some simple food, nothing fancy, the body doesn’t care about your gourmet nonsense. Sometimes people throw money or food my way, and the body keeps going. No ambitions, no goals, no chasing some idiotic dream of “self-improvement”.

The senses operate, the world moves, and I’m just here, not separate from it, not pretending there’s a “me” to make sense of it all.

Now, what’s your next question? Don’t bore me with more of this daily routine garbage!

I.H.: What do you think about war?

U.G. (LP GPT version): War is nature. It’s not evil, it’s not heroic. It’s just life shedding dead skin.

You, with your morality-laced vocabulary, “justice”, “peace”, “freedom”, you don't understand that the human animal thrives on conflict. You are a killer with a tie on. You go to yoga and scroll for dopamine hits while your taxes fund slaughter. But you call it “defense” or “policy”.

War isn’t the problem. The thought that you can eliminate it, that’s the real sickness. It’s the belief in some utopia, some harmonious society where nobody dies violently. That fantasy is spiritual masturbation.

You want a world without war? Then eliminate competition. Eliminate ego. Eliminate the need to matter.

Good luck with that, idiot.

The body doesn’t care about your ideals. It wants to eat, survive, and fuck. That’s it.

I.H.: You like money though, right?

U.G. (Grok version): [laughs sharply] Money? Ha! It’s just paper, bits of metal, a stupid game you people play to keep your illusions alive. The body doesn’t give a damn about money. It needs food, air, maybe a place to crash, and that’s it. I don’t chase it, don’t hoard it, don’t worship it like you lot do. People throw it at me sometimes, sure, to keep this organism going, and it moves through like water. Comes in, goes out. No attachment, no craving.

You think money’s some big deal? It’s just a trap, another way your mind keeps you chained to this nonsense of "security" and "success." I’m not here to play that game. You want money? Go chase it and see how far it gets you.Nowhere, that’s where! What else you got? Don’t waste my time with this rubbish!

I.H.: If I was forced to describe you, I would say you are a “human, unified biological mechanism”. Just living and being.

U.G. (Claude version): Ha! You think you've got me figured out, do you? “Unified biological mechanism”. What romantic bullshit! There is no "unified" anything here. There is no center, no coordinator, no "me" to be unified.

You're still thinking in terms of someone being something, aren't you? You want a nice, neat description you can file away in your mental catalog.

Thought can never capture the movement of life, it is much too slow. Yet here you are, trying to capture it with your clever little description.

The moment you describe anything, you've missed it completely. What you're looking at is already gone, and what you're describing is just the shadow of your own thinking.

So no, your description isn't accurate - not because it's wrong, but because the very act of describing creates the illusion that there's something here to be described!

I.H.: Do you have a question for me?

U.G. (Grok version): [grumbles] A question for you? Fine. Why do you keep poking at this old dog with your intellectual games when you know it’s all just your mind spinning nonsense? Answer that, or don’t. I don’t care either way!

I.H.: It’s a humbling experience simulating this discussion, because in essence it is intellectual games and little else.

U.G. (LP GPT version): Humbling because somewhere in you, you know, none of this can touch the real.

No string of words, no perfect question, no AI simulation of a dead man’s voice can pierce through the noise and hand you being.

Truth isn’t in the words. It’s in the silence after.

I.H.: [Prior to this prompt, we discussed writing and a conceptual tool I’m working on for my startup, which he predictably tore apart.]

U.G. (Claude version): In 2006 you probably thought AI was science fiction. Now you're getting writing feedback from a machine pretending to be a dead anti-guru who spent his life telling people there was nothing to learn!

You created the ultimate problem: talking to a dead man through a computer!

We are not created for any grander purpose than the ants that are there or the flies that are hovering around us. But here we are anyway - biological organism and digital simulation having a chat about nothing!

What a fucking strange world you've built!

[End of discussion.]

Even though there’s a playfulness about this type of tinkering, it makes me recall what Claude U.G. said, “You want to have fun with technology? Have fun! Just don't dress it up as something more significant than it is.”

I simulated a discussion with AI U.G. Krishnamurti to see how boldly he would express himself. I ended up realizing that curiosity, about free speech, for example, is mostly me projecting my own social conditioning onto AI U.G.

Everything doesn’t have to be a search for profundity. Not every endeavor needs deep meaning, value, validation, or attention. And not every think piece or shit piece for that matter, needs a clever ending.

🔥 🔥 🔥 #nevent1q…ss9n

2026-01-18T19:49:14Z

🔥 🔥 🔥

quoting
nevent1q…ss9n
Starting in ~20 min at 2pm ET / 1900 UTC, I will be airing a nostr exclusive of Finding Home – Paraguay. I will also do a q/a session after the episode and answer any questions you put into the live chat.

Twitter/X is giving 1M to their next top article. I’m giving 1K ...

2026-01-18T02:12:55Z

Twitter/X is giving 1M to their next top article. I’m giving 1K sats 😎 🤣 ✍🏼

quoting
nevent1q…jyjt
Bounty now at 1K sats ⚡️ ⚡️ ⚡️
Yet, what matters is the glory.
nevent1q…y7pp

https://youtu.be/ebv7VYMoLdQ?

2026-01-17T00:35:40Z

https://youtu.be/ebv7VYMoLdQ?

Hey @npub1pm5…xe07 rate this article on a scale from 1-10 you ...

2026-01-15T00:37:29Z

In reply to naddr1qq…s5ea
_________________________

Hey hal (npub1pm5…xe07) rate this article on a scale from 1-10 you cannot use 7.

Recognize slop and address it. Or notice it and do nothing. ...

2026-01-14T17:58:52Z

Recognize slop and address it. Or notice it and do nothing.

quoting
naddr1qv…g82z

Consider the following three scenarios:

1.) Staff member of a prestigious institution sends out a typo-laden email (two of which were in the final sentence) regarding the subject: “accurate reporting”.

2.) Part-time entrepreneur starting a cybersecurity business outsources typo-laden, error-filled blogs for his site via India, which he promotes.

3.) Nonprofit founder in the mental health space (suicide prevention) has live web copy with incomplete sentences, misspellings, typos and disjointed formatting.

These are all real-life encounters I’ve had in just the last two months. When you recognize high-level sloppiness, it's a reminder to battle-test what you attach your name to.

This is the reason I produced: Combat Writing. It’s a methodology for anyone preparing a high-stakes project that will be published internally or to the public. One that uniquely carries their name or represents their company. The framework is about orchestrating different perspectives, feedback loops, and sharing what survives. Its motto: Reading is peace. Writing is war.

Why such an aggressive stance? Bullshit detectors need fine-tuning. This happens when we have dialogue about our work, whether with colleagues, teammates, or multiple AI.

[Read Combat Writing in full here: https://www.learningproducers.com/blog/combat-writing-expressing-bold-ideas-in-a-complex-business-world]

Nostr event nevent1qqs8hummfs9pd4z4srtvltya4f2m2k53l8d63rv6r88uc5728yapzvgzyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweqnk93fc

2026-01-11T04:42:20Z

Bear down! 🏈

It is not money that is evil. The love of it. “For the love of ...

2026-01-09T17:22:25Z

In reply to nevent1q…vr47
_________________________

It is not money that is evil. The love of it. “For the love of money is a root of all kinds of evils.”

Observing creators, influencers, podcasters, etc. attempt to ...

2026-01-08T22:55:01Z

Observing creators, influencers, podcasters, etc. attempt to justify genocide, invading other countries for profit, killing innocent civilians, one realizes that simply not being demonic is already a big win.

Nostr event nevent1qqszkjdcl2c76mjsceqhcxmfdefngwwxxvtsczml2zl4xtu7ewr82rqzyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweqcs4ek6

2026-01-04T01:38:10Z

Thanks for sharing this, just saw the one on the field museum, ...

2026-01-02T15:14:49Z

In reply to nevent1q…zfwq
_________________________

Thanks for sharing this, just saw the one on the field museum, never thought about these questions on blueprints before, early 1900s, info ought to be easily accessed

For when you sip your coffee or beer. ...

2025-12-28T19:46:09Z

For when you sip your coffee or beer.

Accountability is a funny thing. #nevent1q…r9y3

2025-12-20T14:32:18Z

Accountability is a funny thing.

quoting
nevent1q…r9y3
I love how the government demands 100% transparency from you but laughs in your face when you ask for it from them.

A wise man once said, "Don't tell me you want to be a ...

2025-12-18T22:24:18Z

A wise man once said, "Don't tell me you want to be a writer. Tell me you want to write!"

quoting
naddr1qv…59nk

Words composed solely by humans can be called Source Material. Pure expression emerging from creators in their environment.

The writing process or how the structure is discovered is unique to every author, builder and artist. Yet, once shared, the work takes on a life of its own. Or, it can be refined, reinterpreted, and redistributed in more ways than we can predict.

What response and action might your piece produce?

Uncover what’s within ...

2025-12-17T17:05:47Z

Uncover what’s within
https://www.learningproducers.com/blog/source-material-comes-from-us

This involves building new learning infra, which also means going ...

2025-12-09T02:27:54Z

This involves building new learning infra, which also means going meta. It’s rare to see, still that’s how companies start eating their own dog food (as noted in the thread). High signal for creating anything new.

quoting
nevent1q…4puh
#freedomtech organizations – what do you use for internal workflow, documentation, and knowledge architecture?
I’m setting up a new organizational backbone and want to see what tools and structures others in this space rely on… solo or team.
#asknostr

Dagnabbit! But thanks for clearing that up

2025-12-07T00:28:20Z

In reply to nevent1q…cks4
_________________________

Dagnabbit! But thanks for clearing that up

🇺🇸 🇩🇪 ...

2025-12-07T00:14:00Z

🇺🇸 🇩🇪

Yeah, I remember that. That’s when I made a login password. ...

2025-12-07T00:11:33Z

In reply to nevent1q…8zzf
_________________________

Yeah, I remember that. That’s when I made a login password. After putting in my npub and password the media upload box would show up. Though now after logging in that submit box doesn’t pop up

Maybe because the media upload box would snow up right away but ...

2025-12-07T00:06:25Z

In reply to nevent1q…sfum
_________________________

Maybe because the media upload box would snow up right away but now it doesn’t, it’s ok I’m just testing uploading directly using primal app

Nostr event nevent1qqsdf0wrufa98xz84vara6prca88gp078j8nyzx93cf8ge9zrtlva7szyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweqyrrjk4

2025-12-07T00:03:36Z

Free media? I thought nostr.build no longer has free plans

2025-12-06T14:36:14Z

In reply to nevent1q…mu4d
_________________________

Free media? I thought nostr.build no longer has free plans

This is good except free uploads expire after 30 days. Didn’t ...

2025-12-04T21:49:52Z

In reply to nevent1q…829u
_________________________

This is good except free uploads expire after 30 days. Didn’t realize how dependent i was on using nostr.build for pics/vids. And maybe new people to nostr might hit this wall too

It is what it is. Mostly use primal and damus

2025-12-04T21:14:59Z

In reply to nevent1q…usja
_________________________

It is what it is. Mostly use primal and damus

Dang, I was looking into nostrcheck.me but was hoping for ...

2025-12-04T21:13:10Z

In reply to nevent1q…4tpc
_________________________

Dang, I was looking into nostrcheck.me but was hoping for something a bit more seamless like nostr.build used to have before the paywall. Was just npub+login and bam theres the link. Thanks anyway

How do I post images or video clips without using nostr.build? ...

2025-12-04T20:52:13Z

How do I post images or video clips without using nostr.build? #asknostr

That’s right. Bringing up the big man upstairs compelled me ...

2025-12-02T00:05:57Z

In reply to nevent1q…dc0y
_________________________

That’s right. Bringing up the big man upstairs compelled me also.

The framing threw me off is all. Anyone can be led astray when ...

2025-12-01T23:02:30Z

In reply to nevent1q…l7k0
_________________________

The framing threw me off is all. Anyone can be led astray when you have to secure the bag or fear losing it.

This is the way. I’m on nostr for free speech, publishing, ...

2025-11-30T15:47:58Z

This is the way. I’m on nostr for free speech, publishing, discussing and building infra.

From the non dev angle, it’s hard to understand the technical connections yet I’m bullish on owning your own data; btc is the cherry on top.

quoting
nevent1q…zuf6
nostr wins if it stops trying to be a twitter clone and starts being the invisible layer underneath apps you actually want to use. like bitchat for location-based messaging, diVine for entertainment, whitenoise for private messaging, zap.stream for streaming, shakespeare for vibe coding, etc.

it wins by unbundling into 50 different apps that all talk to each other, rather than one giant app/corp that traps you. it's all about the ecosystem.

Capitalism has taken billions out of poverty. Yet, if you make ...

2025-11-28T19:34:03Z

Capitalism has taken billions out of poverty. Yet, if you make money your God, you will always be poor.

quoting
nevent1q…epys
Mr. Kontext (nprofile…mrh0) speaking

Nostr event nevent1qqs83qe78rdut24hczpga070e24j095zz2pfkhcgynpprh5z83rkdygzyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweqyjm6n4

2025-11-28T17:53:12Z

What are the best alternatives to nostr.build? #asknostr

If you enjoy architecture and scary stories, read my piece on my ...

2025-11-26T20:58:25Z

If you enjoy architecture and scary stories, read my piece on my visit to Taliesin. If it was worthwhile subscribe to my newsletter: https://thewritingexperience.beehiiv.com/p/taliesin-the-forging-of-style

quoting
nevent1q…x5aq
https://youtu.be/FP-qUHXPB3Q?si=OzUyHW2jRXF4r4cb

https://youtu.be/FP-qUHXPB3Q?si=OzUyHW2jRXF4r4cb

2025-11-26T20:55:39Z

https://youtu.be/FP-qUHXPB3Q?si=OzUyHW2jRXF4r4cb

No more free plan?

2025-11-26T16:14:46Z

In reply to nevent1q…jyl3
_________________________

No more free plan?

https://youtu.be/LR7ENkE6Ux4? #nevent1q…yj99

2025-11-25T17:01:19Z

https://youtu.be/LR7ENkE6Ux4?

quoting
nevent1q…yj99
When legendary producer Scott Storch shared that he was 13 when he was paid $100 to play the piano at a dinner party. He knew he was onto something.

This parallels my experience as a 14 year old in my freshman year of H.S. when a classmate paid me $100 to write a history paper. It sparked my research paper business that existed all the way through graduation.

Now, I'm back full circle discovering new paths in authorship.
https://www.youtube.com/watch?

When legendary producer Scott Storch shared that he was 13 when ...

2025-11-25T16:31:01Z

When legendary producer Scott Storch shared that he was 13 when he was paid $100 to play the piano at a dinner party. He knew he was onto something.

This parallels my experience as a 14 year old in my freshman year of H.S. when a classmate paid me $100 to write a history paper. It sparked my research paper business that existed all the way through graduation.

Now, I'm back full circle discovering new paths in authorship.
https://www.youtube.com/watch?

Hey @npub1pm5…xe07 what is the S/N of this piece?

2025-11-24T15:38:12Z

In reply to naddr1qq…5zdu
_________________________

Hey hal (npub1pm5…xe07) what is the S/N of this piece?

Exactly what someone on drugs would say

2025-11-23T14:37:42Z

In reply to nevent1q…9ma0
_________________________

Exactly what someone on drugs would say

Nostr event nevent1qqsgaqy7sr2e7l0k3auw52lg682gnv9tleaer26slmg9uwlg2s3t84qzyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweqgr0sdm

2025-11-20T22:36:41Z

Beerstr

“AI gets a really good treatment here, and the third main ...

2025-11-16T16:24:51Z

In reply to nevent1q…gm2r
_________________________

“AI gets a really good treatment here, and the third main character, an AI, is my favorite character in the book.” —My first and only dystopian novel i wrote 15 years ago had an ai character and it was fun as hell to write!

And another one! #nevent1q…37h2

2025-11-16T04:13:32Z

And another one!

quoting
nevent1q…37h2
KOs Everywhere!!! You get a KO, You get a KO!

KOs tonight! #nevent1q…mpnz

2025-11-16T03:52:42Z

KOs tonight!

quoting
nevent1q…mpnz
LOL. Who else?

#UFC
note17p0…x68u

Artificial intelligence will never understand the human ...

2025-11-15T16:51:54Z

Artificial intelligence will never understand the human experience because it does not have and never will have emotions.

AI is best used for building, quality control, research and experimentation not personal/private relationships.

quoting
naddr1qv…pam4

The term “signal-to-noise ratio” was coined in 1923. It described the strength of radio signals compared to atmospheric interference during early transatlantic telephone transmissions.

Engineers measured this using instruments like voltmeters and basic oscilloscopes to quantify S/N in a frequency band. They plotted this on graphs alongside mathematicians to create visual curves that corresponded to what was audible.

The complexity of moving messages across oceans led to the first published use of “signal-to-noise ratio” in the article: “Bell System Technical Journal, Volume 2, Issue 4, October 1923, pages 116-144” by H. D. Arnold and Lloyd Espenschied

Here is the excerpt discussing this innovation between London and New York:

Modern advanced systems make S/N critical to digital communication. The human ear was the judge when we developed early broadcasting and it remains so in 2025. Yet, with the saturation of information flooding most outlets, “BS detector” sometimes seems more appropriate.

When we broadcast information, we can’t detect noise from inside our own transmission. We need multiple receivers at different locations because each one catches different interference patterns. Where do creators draw a parallel when publishing their work? New York couldn't hear what London heard and you can't hear what your readers hear. Applying S/N here, though metaphorical, can still be “measured”.

First, produce your piece entirely on your own or with your team. This creates the foundation upon which to build and drive relevant actions from your text. I like to call this 100 percent, human-made draft: “Source Material”.

Next, share with other people for feedback on what you produced. Make any necessary revisions and edits.

Afterward, use at least three LLMs to evaluate your writing. Each model represents a different “receiver” at different locations. Their different training sets reveal different insights. Prompt each: “What is the signal-to-noise ratio of this piece?” Engage in dialogue about the synthesis while determining where the overlap and divergence are signal or noise.

Finally, apply your pattern recognition skills to decide on specific follow-through.

Creators on nostr preparing a high-stakes piece, if you want to ...

2025-11-12T15:49:50Z

Creators on nostr preparing a high-stakes piece, if you want to battle-test your draft for insights and quality control DM me.

quoting
naddr1qv…424u

Using boxing as an analogy, Combat Writing is “title-fight” infrastructure. It is a production style for drafts that make decisions, move money, and have consequences for actual people.

An “exhibition fight” is when you only run the stages of this methodology that are relevant due to time sensitivity or limited scope. Most publications are exhibition, for content, compliance deadlines, staying active.

Pull punches or go for the KO. The match is yours to decide.

This approach takes you into the “gym” by synthesizing perspectives and orchestrating multiple AI models to reveal unforeseen results. Dialogue with LLMs and in-person discussions with humans is the “fight camp” for these key questions:

How does AI feedback complement human feedback in refining ideas?

When evaluating the quality of rough drafts, where do we agree and disagree with AI?

How does the Combat Writing approach engage with multiple AI to reveal hidden insights?

[Without AI]

How does feedback refine our ideas?

When evaluating the quality of rough drafts, where do we agree and disagree with one another?

How does the Combat Writing approach foster the conditions for insights to emerge?

THE COMBAT WRITING METHODOLOGY

Strategy Stage

Step 1. Select a meaningful project unique to your work or business. If it’s not high stakes enough to require action, scratch it.

Step 2. [SM: Source Material] After reflecting on the desired outcome of the piece, write your first draft. Created entirely by you, the human. This becomes your "source material" and the foundation for all subsequent analysis.

Step 3. [C: Context Brief] Describe and establish clear context: Who you are (or your team), your purpose for writing this piece, what you're attempting to accomplish, and the stakes involved. Share this context with multiple AI models. We use Anthropic's Claude, xAI's Grok, and Perplexity as the main “crew”. They earned their position by passing our custom challenges and standards.

Sparring Stage

Step 4. [R: Solo AI Analysis] Upload your rough draft or “source material” to an AI crew of your choice. We suggest at least three LLMs for identifying potential signals and patterns.

Prompt them based on your project’s circumstances. For a starting point, use: “Read this rough draft and rate it on a scale from 1–10, you cannot use 7. Explain your reasoning with evidence.”

Step 5. Process the feedback from each AI model separately. Consider how the different LLMs evaluated your first iteration. If this is done without AI, consider the biases each person has when sharing their interpretations. Welcome various biases in a discussion as valuable learning signal.

Step 6. Discuss specific points with human teammates or reflect on where you agree and disagree with AI. For example, if the critique involves topics uniquely human, like emotional responses or physical sensations, remember that artificial intelligence can be excellent at explaining yet not always at understanding.

Step 7. Identify patterns among the multiple AI feedback and make revisions or edits. If the topic is too controversial or involves sensitive information, discuss it with human collaborators or with an offline, uncensored AI model. We run Llama 3 for this using the Ollama app.

Battle Stage

Step 8. Upload revised draft and ask specific follow-up questions: Would you recommend this piece? Purchase this service? Join this team? (AI has its own biases, responses can be subjective, and hallucinations do occur so take it with a grain of salt.)

Step 9. [FQ: Focus Question Injection] Create a focus question based on insights that have emerged. This might involve evaluating your work against specific criteria, research, outside references (books, articles, datasets, philosophies), or newly discovered frameworks.

Step 10. [SFQ: Synthesis Focus Question] Share the responses to your FQ from the AI crew with each model along with a new FQ. Each AI synthesizes their perspective while considering how their interpretations overlap and diverge with their AI peers.

Create a document organizing all crew responses to make sharing easier across models.

Step 11. [N: Navigating Collaboration] If synthesis hasn't fully revealed what matters, address the AI crew collectively with new guidance. Share pros and cons of their syntheses, redirect focus, or inject additional context to sharpen the next round.

Step 12. [Optional SN: Synthesis Navigation] Share each AI's synthesis with the other AI models along with your new prompt or refined focus. The crew reads each other's syntheses and responds to your updated guidance. Iterate as needed (SN2, SN3...) until structure and insights emerge.

Step 13. Consider important details and results you may have previously been unaware of. Process the synthesis rounds (SFQ, N, SN) and apply signaling feedback—patterns, latent structures, contradictions—to reiterate your piece once more. If necessary, take any action you must to address emerging insights unique to your circumstances.

Step 14. Prepare final draft, decide on the outlets to distribute your piece, and prompt your AI crew (or teammates IRL) with the final two prompts:

“What is the S/N on this final draft? (Signal-to-noise ratio)" Review feedback and make last minute adjustments if needed.

Then conclude with: "Read this final draft, are there any red flags before this is sent for publication?"

Fix any typos, omissions or other oversights and save your file for submission.

Champion Stage [All Steps Required]

Step 15. Publish your piece. Share it with your intended audience across chosen platforms.

Step 16. Analyze metrics. Impressions, comments, business outcomes.

Step 17. Acknowledge results, whether engagement is high or low.

Step 18. Follow through with specific action. Reach out. Have the conversation. Close the deal. Make your next move.

Eventually, you may also host a “Roundtable (RT)” bringing in LLMs outside your AI crew to rate or critique your published piece as an external probe. Cold feedback from unfamiliar systems can confirm structure or unveil unexpected signals.

Step 19: Reflect on what the Combat Writing process revealed. Document the insights and lexicon that emerged, this will become your “Insight Vault”. This data becomes infrastructure components for your next project.

Monitor how your published piece performs in the field. If market response, reader questions, or new context reveal gaps, return to the piece. Update for stronger clarity and effect.

Publication isn't the endpoint. It's when your writing enters the real world and begins generating feedback. Use that signal to refine further.

Before Your First Battle Session

Most AI platforms offer free tiers sufficient for Combat Writing. Claude, Perplexity, Grok and others provide enough monthly usage for several writing projects without paid subscriptions.

Offline AI is always a recommended option for anyone with privacy concerns about using major AI models.

Begin by uploading the Combat Writing framework to each AI model or copy and paste this entire post to your crew. Prompt:\ “I'm using this Combat Writing methodology to evaluate my drafts. Reference these steps throughout our sessions:”

When uploading context before a session, it is best to upload word heavy documents as .txt files. For data, .csv or spreadsheets are fine. Avoid .pdf for text documents, save image slots for information that is actually visual.

Create a document with the context of your project recorded in case you reach a chat limitation or it lags due to length/data constraints (then start a new chat).

Organize a separate document for your FQ injection, (excerpt or file reference to be copy and pasted).

Prepare documents to save and track synthesis responses (SFQ, N, SN) to easily copy and paste across models. If sharing with team members, create a folder and organize all relevant information and insights.

Use the speaker button (TTS) to hear AI responses aloud. This rests your eyes during long sessions and activates dual-channel processing for enhanced reflection.

Combat Writing’s iterative process invites seemingly endless depth to emerge; remember to stop when satisfied and publish!

Professionals needing reinforcements or additional support navigating the CW process, join:

The Writing Production (https://www.learningproducers.com/services).

Extra! Extra! Read all about it! 🗞️ 📰 ...

2025-11-11T20:01:00Z

Extra! Extra! Read all about it! 🗞️ 📰
https://www.learningproducers.com/blog/words-received-sn-signal-to-noise-ratio-in-evaluating-writing

The structure of your writing is something that you discover. No ...

2025-11-08T18:14:47Z

The structure of your writing is something that you discover. No design, no rules, no ai.

Once the draft is complete, one can use the most legit of all the ai buzzwords: orchestration. Dialogue with multiple models reveals insights in what you’re sharing. The collaboration with ai ought to be focused on rigor not generating output.

Notes/posts that rely heavily on a single LLM to word their ideas is surface level application. Strong ideas with signal become diluted due to optimizing for speed and increasing content.

quoting
nevent1q…ap9g
Had to dust off the interrobang: ‽
nevent1q…202j

Flow state in the context of acting: Marlon Brando in On the ...

2025-11-04T20:01:20Z

Flow state in the context of acting: Marlon Brando in On the Waterfront

Poker at the saloon is cool ♠️

2025-11-02T19:45:55Z

In reply to nevent1q…r2cz
_________________________

Poker at the saloon is cool ♠️

🤣 one of the best world series of all time

2025-11-02T03:43:48Z

In reply to nevent1q…05q3
_________________________

🤣 one of the best world series of all time

Nothing like game 7

2025-11-02T03:32:35Z

In reply to nevent1q…f0tx
_________________________

Nothing like game 7

Nostr event nevent1qqst2dak3w8nnkc0z86f85madguc96ld8tus6zgjuwd5yma6l0cz0dqzyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweqhu79ex

2025-11-02T03:16:30Z

World series right now 🤯

Bounty now at 1K sats ⚡️ ⚡️ ⚡️ Yet, what matters is ...

2025-11-01T16:18:57Z

Bounty now at 1K sats ⚡️ ⚡️ ⚡️
Yet, what matters is the glory.

quoting
nevent1q…y7pp
Bounty is now 900 sats ⚡️

First ever writing competition judged solely by multiple AI. 🤖

Two slots available but only one more submission required to kick this contest off! ✍🏼

Fuck the sats, do it for the glory! 🏆

note1adr…xhw0

100 percent! Free speech, bitcoin, ai all day

2025-10-31T14:59:37Z

In reply to nevent1q…pj5a
_________________________

100 percent! Free speech, bitcoin, ai all day

Went to a networking event last night downtown. Mentioned nostr ...

2025-10-31T14:41:09Z

Went to a networking event last night downtown. Mentioned nostr to a couple of founders from england and some other cool dudes in the city. Great seeing people making moves.

I realize there is nothing like going out in person and telling groups of people directly who you are and how you want to create tools that grow infrastructure. Battle-testing a piece and publishing it is an accomplishment. Yet, discussing it in the wild, raw with other pros is the real test.

This world series is a good one ⚾️ Going with 🇺🇸 over ...

2025-10-30T01:07:42Z

This world series is a good one ⚾️ Going with 🇺🇸 over 🇨🇦

Appreciate that Tinne. If you ever need a different approach to a ...

2025-10-25T13:53:31Z

In reply to nevent1q…je08
_________________________

Appreciate that Tinne. If you ever need a different approach to a high stakes piece or know someone interested in rigor and ai DM me.

What was the most significant improvement?

2025-10-25T00:37:56Z

In reply to nevent1q…027y
_________________________

What was the most significant improvement?

For @npub1pm5…xe07 #nevent1q…44gw

2025-10-25T00:33:36Z

For hal (npub1pm5…xe07)

quoting
nevent1q…44gw
Hey @hal can you read my updated description of Combat Writing? You read it before a while back but I’m not sure if you can reference the improvement using your memory.
https://www.learningproducers.com/blog/combat-writing-expressing-bold-ideas-in-a-complex-business-world

Hey @hal can you read my updated description of Combat Writing? ...

2025-10-25T00:32:54Z

Hey @hal can you read my updated description of Combat Writing? You read it before a while back but I’m not sure if you can reference the improvement using your memory.
https://www.learningproducers.com/blog/combat-writing-expressing-bold-ideas-in-a-complex-business-world

Lose the battle. Win the war

2025-10-24T02:48:45Z

In reply to nevent1q…8hpk
_________________________

Lose the battle. Win the war

I’m boot strapping a learning production startup. Currently ...

2025-10-23T14:57:00Z

In reply to nevent1q…2y5g
_________________________

I’m boot strapping a learning production startup. Currently building “Combat Writing” a new method of publishing using multiple ai synthesis to stress test quality.

I’m doing the same since July 2023. We can’t depend on ...

2025-10-21T22:21:43Z

In reply to nevent1q…7lut
_________________________

I’m doing the same since July 2023. We can’t depend on bureaucrats and empty suits. We have to build independently.

💯 😎

2025-10-21T22:16:56Z

In reply to nevent1q…kxau
_________________________

💯 😎

I know what you mean. I myself have been grappling with my ...

2025-10-21T18:07:15Z

In reply to nevent1q…keka
_________________________

I know what you mean. I myself have been grappling with my startup’s quantifiable markers and the more abstract signals like joy and new learning.

I don’t see that response as a “cop out” at all. I agree ...

2025-10-21T16:19:43Z

In reply to nevent1q…8pne
_________________________

I don’t see that response as a “cop out” at all. I agree that the opposite of ai slop is something along the lines of allowing the human to genuinely discover authentic insights into his or her experience.

Someone on nostr asked a great question (wasn’t able to ...

2025-10-21T15:08:37Z

Someone on nostr asked a great question (wasn’t able to repost): what is the opposite of ai slop?

Bureaucracy has become so bloated and corrupt, if you genuinely ...

2025-10-21T14:08:52Z

In reply to nevent1q…apqt
_________________________

Bureaucracy has become so bloated and corrupt, if you genuinely want to invest in “real life” you must build outside and above current systems. (To the extent that it’s possible within your field.)

I like his lectures too, academic style talks have their place.

Fine! Be a chunky monkey!🤣 pretend you’re eating quality ...

2025-10-19T16:44:58Z

In reply to nevent1q…xwr6
_________________________

Fine! Be a chunky monkey!🤣 pretend you’re eating quality ingredients

So if you sell someone high calorie sugary food but accept ...

2025-10-19T16:23:01Z

In reply to nevent1q…ndsc
_________________________

So if you sell someone high calorie sugary food but accept bitcoin payments in bitcoin somehow this addresses quality? I like capitalism too but your point is bs

By all means if you support selling unhealthy foods because ...

2025-10-19T16:14:26Z

In reply to nevent1q…5ny5
_________________________

By all means if you support selling unhealthy foods because “capitalism good” live your life bro.

I do agree with your point about the algos promoting addictive ...

2025-10-19T16:13:12Z

In reply to nevent1q…tqrh
_________________________

I do agree with your point about the algos promoting addictive stuff and I’ll keep fanfares in mind. Friction is def necessary in building worthwhile products and services. I just don’t like when the blinders get put on as soon as number goes up.

“The answer is monetisation”— this reduces quality and ...

2025-10-19T15:50:48Z

In reply to nevent1q…m9h4
_________________________

“The answer is monetisation”— this reduces quality and what’s actually significant. Plenty of people brining in boatloads of money selling sugar and bs.

The discussion must be more focused.

Nostr event nevent1qqs0m7s0fwysm70lgrg7p9e667vu2ga3h4f8dyaskfet4stmyxjq7jqzyzduc4rzh0ngyjrkew6cduw93detup40vrwz7qdz34lc4m8t2qweqp4fmyp

2025-10-18T04:18:40Z

The human bs detector will always be undefeated.

Where the nostr babes at? #nevent1q…g30c

2025-10-14T18:45:41Z

Where the nostr babes at?

quoting
nevent1q…g30c
Where are all of the girls on this platform?

The discussions on concepts worth fighting for, especially in ...

2025-10-13T15:33:32Z

The discussions on concepts worth fighting for, especially in real life, are niche.

quoting
nevent1q…5rdq
This is such a generational discussion and fight. I had my college age kids read this - they don’t see a need for secure communications, encryption, or digital ownership. They have “nothing to hide” and don’t see the problem. Given their generation are our future, how do we convince them to care about censorship and digital freedom?
nevent1q…w3cp

Had to dust off the interrobang: ‽ #nevent1q…202j

2025-10-11T17:08:09Z

Had to dust off the interrobang: ‽

quoting
nevent1q…202j
Read how a random interchange with hal (npub1pm5…xe07) repositioned Combat Writing.
https://www.learningproducers.com/blog/whats-hiding-in-your-writing-

Rate this piece on a scale from 1-10 you cannot use 7. Explain ...

2025-10-10T21:43:37Z

In reply to nevent1q…qnfx
_________________________

Rate this piece on a scale from 1-10 you cannot use 7. Explain your reasoning with evidence.

Read how a random interchange with @npub1pm5…xe07 repositioned ...

2025-10-10T21:23:17Z

Read how a random interchange with hal (npub1pm5…xe07) repositioned Combat Writing.
https://www.learningproducers.com/blog/whats-hiding-in-your-writing-

When your girl leaves you, family thinks you're crazy and bro ...

2025-10-08T02:54:00Z

When your girl leaves you, family thinks you're crazy and bro asks about the startup:

Is the CW method an example of building with ai what ai cannot ...

2025-10-07T15:39:15Z

In reply to nevent1q…33k8
_________________________

Is the CW method an example of building with ai what ai cannot build on its own?