If prayer is you talking to God, then intuition is God talking to you.

The more I’ve gotten these God shot intuitive moments the less I attribute them to “me“ and more to some higher outside force that acts as a guide. I think for a while I used to like to take credit, but really this was just my ego taking credit for things it didn’t understand.

When I’m making my “own” decisions, I tend to be brought down the wrong path, have the wrong timing, and fail to consider every option. When I’m making decisions from my intuition or “gut” as most people call it, then I rarely (never) make missteps and am often executing at my peak. When building anything (companies, relationships etc) the biggest barrier is lost time—not money or resources. Intuition acts as a shortcut that helps you make the right decisions at the right times to make the right calls.

When you discover this, it becomes imperative that you’re always making decisions from the position of your intuition instead of your rational mind. My mind has trained me that it is most likely wrong, whereas my intuition is almost always right.

The Impact of Feelings and Emotions

I used to not like certain emotions. I thought I wanted to be “happy“ or in some way more free. More recently though I’ve started to think about emotions as “raw intuition“ that hasn’t been fully processed. Most often, when I process those emotions, at the end I find myself receiving some form of intuition that ends up benefits me, helps me solve some previously unsolvable situation, and helps me avoid the pitfalls that would take more time or be exhausting.

For a long time I didn’t think I wanted to feel fear, sadness, or disappointment. The truth is that these serve me quite well! The problem is when I avoid them and let them fester because it delays getting to the right action that comes at the end of letting that intuition be fully formed.

It’s actually great to have fear or anxiety, it means you’re on your way to getting the piece of intuition you need to move beyond that problem. Where things get sticky are when you avoid or deflect and try to not feel that feeling. Often times avoiding it leads me to taking some defective or self serving action. The point is to feel the feelings to help you get to clarity! The more you lean into feeling it and understanding it the sooner you can get to a resulting correct action.

I spent a long time in life trying to not feel feelings rather than understand them, strongly to my detriment. This is understandable! Especially in critical situations these feelings can be overwhelming. The best way to work with feelings is to note them, get curious, and process them thoroughly so you can find those intuitive decisions at the end of the tunnel.

Reactions and Responses

When I first started working on companies, I would have emotional reactions to everything. Some concrete examples of things that are emotionally reactive:

• Firing an underperforming employee before finishing a PIP

• Lashing out at a lead investor for saying that we should have raised at a higher valuation

• Firing a cofounder for being on Twitter too much

In these moments where emotion meets rationality, it is easy to make the wrong decision with the right inputs. This is reactivity. The same feelings though when processed can become a superpower. When you’re afraid of that employee impacting the team, that investor not having the company’s best interest at heart impacting a board, or the cofounder’s ego getting in the way

Sometimes these might be the right actions but the wrong reactions that led to them. There are valid reasons for responding differently:

• Firing the employee can be the right decision, but it’s also important to send the right message to the rest of the team

• Flagging that investor might not have the companies best interest at heart

• Resetting team culture to be low ego and high ownership

Conclusion

Intuition or gut based decision making is a superpower when it comes to building companies and many things in life. There’s a key to working with it that requires you to love and lean into feelings with curiosity rather than aversion or fear. The end result too is not running from feelings like I was but actually using them as leverage and tools to level up how you make decisions and navigate the world.

It feels like every day I see new launches around speculative / crypto driven businesses. I don’t think any of these things are inherently bad - speculation should be legal but I think the industry as a whole is missing tons of guardrails when it comes to marketing what these products truly are to retail investors. Every time I see it, it makes me angry.

The way that these products are being marketed masks the risk to retail investors who do not understand the way that proprietary trading and marketing making works in sophisticated markets. I believe these investors should be allowed to trade in these markets by virtue of freedom, but I don’t think the companies that are winning deserve the right to mask the risk or who they are trading against.

The thing that makes me the most frustrated is because the marketing and dealmaking rules aren’t clear it disadvantages the entrepreneurs trying to do things fairly - it’s impossible to win by playing fair in these markets against large companies that are being sleezy by masking the risk, creating social media hype that doesn’t disclose the way the markets work, and only catering to a small set of professional traders rather than every day users. I’ve lived the reality of competing with cheaters directly and it pisses me off that the cheating is still ongoing. By principle, when I was working in crypto I never did influencer or prop trading deals or traded meaningfully myself. We just let markets play out naturally. It’s disgusting and not something I want to be around. I’m embarrassed I was ever associated with the industry, and embarrassed for some former colleagues for engaging and profiting off of it.

We need better laws.

/endrant

Great song with a good message.

The mere-exposure effect is a psychologicalphenomenon by which people tend to develop a liking or disliking for things merely because they are familiar with them. In social psychology, this effect is sometimes called the familiarity principle. The effect has been demonstrated with many kinds of things, including words, Chinese characters, paintings, pictures of faces, geometric figures, and sounds.^[1] In studies of interpersonal attraction, the more often people see a person, the more pleasing and likeable they find that person.

One core question to digital media: are you reading from the algorithm or is the algorithm writing you?

Just how there might not be “democrats” and “republicans” but instead “cnn viewers / NYT elites” and “Fox News viewers” there might actually be splits in belief based on if you’re a “instagram user” or “TikTok user”

Good food for thought :) .

I think there is this really interesting distinction that most people who work in software don’t quite grasp. There is a sharp difference between a “startup” and just a “business.”

The Startup Delusion

A startup is a business, sure, but it’s a very specific breed. It’s designed to grow extremely fast and capture a massive market. Because of that, these things are super risky. They’re driven mostly by hype and narratives, especially at the very beginning. To be honest, they’re very, very difficult.

When you’re launching a startup, you almost have to be delusionally insane. You have to believe you can capture such a significant part of a market that the risk becomes worth it for the investors, the employees, and yourself. I’ve done a few of these now. In the shortest, most simple way to put it: I’m just sick of trying to be that delusional again.

Trading Hype for Reality

I don’t think I have another startup left in me, and I told my friends that over lunch. Instead, I’d rather go build normal businesses that make money from day one. I like the idea of a model where you can put money into R&D, but you actually know what the investment is and what the ROI looks like. You understand those pieces of risk much better upfront.

There’s still a spectrum of risk, of course. I still want to work on software businesses and similar projects. But the interesting thing about a standard business is that you don’t have those same crushed timelines and wild growth expectations hanging over your head.

Focus and Fulfillment

Without those pressures, you just get to focus on building the thing. You have a much higher hit rate. It’s a lot more fun, and you can still make a lot of money. Plenty of medium-sized business owners make a great living building things that are good for the world and provide solid employment.

You don’t need to do it the way the Silicon Valley ecosystem pushes. I think people get lost in the sauce of the ego trip that startups provide. There is so much external validation involved, but after doing this a few times, I’m just tired of that. I’m more excited about the reality of actually building good software.

The point of all this is to say that I think I’m done with starting startups for a very long time. I still love to build, and I’m excited to find people to build businesses with over my life, but I’m ready to gear my life toward something a bit more grounded.

This year, I set out with five specific targets:

1. Double down on Foundation.

2. Find time for mentorship, teaching, and reading every week.

3. Bootstrap one thing to $10,000 MRR.

4. Find a girlfriend.

5. Make friends at the top of my social stack rank.

Here is where things stand.

The Foundation

On the foundation side, I think I’ve done quite well. I’ve been super consistent with the gym, meditation, and prayer. Most importantly, I’ve been keeping my mind in a really good spot. Honestly, I feel better than I ever have. There is this specific sense of peace in my life right now, and it’s great to finally be in that headspace.

Mentorship, Teaching, and Reading

I haven’t been doing this one super well. I have found decent windows for mentoring, especially through various work projects and writing here on the blog, but the reading side has slipped. I haven’t really finished any major books since January. I’d like to reset that and get back into a better rhythm over the coming months.

The $10k MRR Goal

I haven’t successfully hit this or even really structured my time toward it yet. I think Wrench Desk could potentially get there, but with how my life is set up right now, the sales cycles are just really difficult to manage. Because of that, I’m thinking about going back to the drawing board. I want to spend the next month or two hacking on a few other ideas to see what might have better legs.

Relationships and Social

The girlfriend goal is still a work in progress. That one is pretty self-explanatory.

As for making friends at the top of my social stack rank, this has definitely happened. Even with a bunch of changes at work making it harder to spend as much time as I’d like with people, I’ve made my friendships a huge priority. I’m incredibly grateful for everyone who is in my life right now.

Overall, it’s a mixed bag, but that’s exactly why I do these check-ins. It’s time to double down on the reading and get back to hacking. Thanks for following along.

Most people don’t understand cybersecurity all that well. The reality is that anything out there can be hacked. It’s ultimately just a matter of cost. The best defense isn’t about being unhackable. It’s about making it extremely expensive to access certain systems. When you look at the various layers of security, the certifications, and the different postures companies adopt, that’s what it’s really about: How expensive and difficult are we making it to breach this system?

In the short term, these new models change that equation for everyone. But in the long term, I believe they’ll change it so that breaching the most secure systems becomes significantly more expensive.

The reason is that these models enable automated pen-testing frameworks. If you own your own code, you can have these models audit it as part of your continuous integration and testing. We can catch bugs before they ever ship.

We’re seeing a surge in bugs being found right now, and I’m not sure it’s because the world suddenly became less secure. It’s more likely that people have finally discovered how good these models are at finding existing vulnerabilities. Look at what happened with Firefox: their reports for critical vulnerabilities were fairly low, in the tens, for the last five years. Then, over the last two months, that number picked up significantly, and they fixed over 1,000 in just the last month.

To me, that isn’t a statement on the world getting more dangerous; it’s a statement on how insecure the world already was and a sign of where we’re headed.

I’m actually really excited about these automated testing strategies. We might have a temporary period of turbulence as we adjust, but I think we’ll eventually settle into a new equilibrium where things are much more secure than they used to be. There are incredible opportunities right now for building automated pen-testing into almost every digital surface that exists.

As always, the most vulnerable surface will remain the human layer. Hacks are so often the result of someone being exploited, tricked, or targeted because they were being trusting. It warrants a certain level of paranoia, but for me, this shift is much more exciting than it is scary.

One thing I became obsessed with when I realized this is what I call a “key habit.” This is a habit that, when you do it, causes your other positive habits to happen almost automatically. I spent a long time searching for this a decade ago, before eventually going on a “walkabout” through other areas of life that I’ve written about here.

Recently, I’ve come back to that idea: maybe there really is one key habit for me. One thing that, when I do it every day, compounds into everything else so I can do what is important and good without as much friction or thought.

The Headspace That Changes Everything

If I boil it all down, the most important habit I have is this: every morning, I get on my knees and say a prayer. A lot of that prayer comes down to:

• Making myself more humble.

• Allowing myself to get out of my own head.

• Thinking about other people rather than just myself.

• Practicing gratitude.

Starting the day from that headspace is what makes the other pieces of my life fall into place. As a result, I show up better for the people in my life. I tend to go to the gym. I tend to eat right, avoid alcohol, and maintain all those other small things that add up to be very big things. It fundamentally changes how I live and how I appear to the world.

Heart Space Over Urgency

This habit has been working for me for a little over a year now. What I’ve realized is that many of the things I thought I “had” to do don’t actually require such urgency.

What I do need is to find myself in that right space, approaching life from a higher degree of thinking. It isn’t just about following steps; it’s about getting myself into the right head and heart space so I can show up the right way every single day.

The Limits of “What” vs. the Power of “Why”

Current models are incredibly good at writing lines of code and describing exactly what those lines do. However, they struggle—and often fail—to answer the fundamental questions of the user experience:

• How is this going to make the user feel?

• What is actually useful to the person on the other side of the screen?

• What parts of this interface will be frustrating, broken, or otherwise undesirable?

There is something I can tell a model that it can’t quite grasp itself. I can provide the instructions for what to do, but behind those instructions, there is the why of what to do. In many ways, this bridges my heart and my head in terms of what actually matters for the customer of whatever software we’re building.

Why This is a Risk for Vibe Coding

One of the things that makes me a little bearish, frankly, on the vibe coding concept is that the skill of understanding human impact is one that takes a long time to build. It’s a skill I’ve only ever seen humans truly possess. While I’ve seen the models get a little bit better at guessing what a specific use case might look like, they are definitely nowhere near getting the full thing done.

Furthermore, these advancements don’t actually necessarily speed me up as a developer anymore. I think the biggest speed increase I got was when GPT-4 came out. It could knock out almost perfect code; I could provide a few files, give specific instructions, and it would write the code pretty much bug-free as long as I was descriptive enough about exactly what I was asking it to write.

Today’s models are basically that, except with agentic harnesses; they are better at exploring codebases and understanding where to make changes, so I can be a little less specific in my descriptions. But the thing I’ve realized is that if I don’t understand how the product works myself anyways, I have a really hard time actually creating the experience that is necessary for end users.

The Plateau of Usefulness

I don’t know exactly where we go from here, but my intuition is that the models themselves are starting to slow down in terms of their usefulness, especially to engineers. They might still be quite useful to many other disciplines going forward, especially as other people ramp up on them.

I’m not saying Twitter is inherently bad, but the way it’s structured today is definitely a problem. The algorithm is built to reward attention-seeking behavior rather than reality-seeking behavior. It turns out that the things that get the most attention are often the least real, and the systems we have in place, like Community Notes, are just completely insufficient for telling the truth.

Marketing vs. Merit

You end up with this huge bucket of consumers who believe whatever is happening on their feed. This forces companies to be extremely reactive because the Twitter zeitgeist can actually move the needle.

A perfect example of this is the debate between Claude and OpenAI’s Codex. If you talk to programmers who use both, most will tell you that Codex is the better product. But because the Anthropic team was able to manufacture this super viral loop on X, it almost destroyed the concept that the best product wins. Maybe the best product wins in the long term, but in the short term, the best-marketed product is winning. I don’t think that’s actually good for the world.

The Viral Loop Problem

The way people have figured out how to “hack” these algorithms for viral marketing moments isn’t a great mode for building products. It damages the world way more than we realize. On some platforms, maybe a viral loop is fine, but if Twitter is supposed to be our digital town square, we need a correct way of moderating which voices are heard. We need to know that those voices are being truthful.

The Reality of Groupthink

I don’t think it’s been all bad, and I think Elon actually has good intentions for the platform. But it’s become so political that everything has just averaged out to groupthink. Whether it’s on the left or the right, these algorithms pump narratives at us that are really hard to distinguish from reality.

In the long term, that’s just not good for society. It leads me back to the same conclusion: this is exactly why we need to regulate social media. We can’t keep letting the loudest, most viral voice dictate the reality of our businesses and our lives.

Early on, I was floored by our traction. We had real legs. But about a month in, I noticed something that didn’t add up.

We had social engagement that rivaled some of the biggest projects on base, yet their trading volume was multiple orders of magnitude higher than ours. Their prices were mooning; ours were moving normally. I’ve always believed crypto is good for two things: large-scale stablecoin transfers and upfront speculation. I have no problem with speculation, as long as everyone knows that’s what they’re doing and that the projects are marketing things not as products but as entertainment assets which we did through and through.

As I started digging into the data in December 2024, I realized the game was rigged.

The “Market Making” Illusion

What I discovered and what has since started trickling out in various lawsuits is a massive game of market manipulation.

Here’s how it works: Teams hand over a massive percentage of their token supply to “trading firms.” These firms then become the “house.” They provide the liquidity, meaning every time an average user trades, they are trading directly against a professional firm with an infinite information advantage. In some cases, they even coordinate with MEV (Miner Extractable Value) bots to effectively strip-mine the end consumer.

We didn’t do that. Our growth was organic, which meant our charts looked “normal.” But because we weren’t rigging the engine, we couldn’t compete with the “success” of projects that were.

When the Data Got Dangerous

On Christmas of 2024, I started posting raw data to X. I didn’t make accusations; I just posted the numbers we found on Dune Analytics. I wanted to show the community the reality of these shadow markets.

That’s when things got dark.

I started receiving what I’d call “backhanded blackmail.” Anonymous accounts, some years old, started dropping personal details about my life that weren’t public into random chats. Some of it was related to my past struggles with alcohol (something I’ve worked hard to overcome), but other details had no digital footprint and pointed to members of my family. It became clear that I was being followed in person.

I was terrified. Not just for my reputation, but for my safety and the safety of those around me. By March 2025, I took my name off the project. I stepped back. And because these were culture-led tokens, the culture fades, and the tokens lose value. I chose to hold what small parts I had to zero too so that I didn’t betray the community for those memes. I felt like I couldn’t explain why I was leaving though without publishing the full data, which felt like a reckless move that would put a target on my back and those I love.

Finding the Middle Ground

I’ve done a lot of inner work since then. The fear is still there, but it’s quieter now. I’ve tried writing about it several times but this moment in time feels more right.

It hasn’t sat right with me that the current regulatory environment actually seems to protect the manipulators while punishing the builders. We’ve reached this weird polarized state: either “crypto is all evil” or “deregulate everything.”

The truth is in the middle.

I believe speculative art and entertainment assets should exist. There is clear product-market fit for the “absurdity” of things like ConstitutionDAO or the entertainment assets we were allowing people to create. People love being part of a viral moment. But that shouldn’t require a market structure that enables teams to hide behind thousands of addresses to fake traction and manipulate prices.

I’m writing this today because I care. I was outspoken behind closed doors with ecosystem leaders back then, and it saddened me how few (none) were willing to stand up for the average person getting liquidated by shadow market makers. I was wrong about this market.

I tried to be that person, and I got threatened for it. But I’m still here, and I still believe we can do this better. We need transparency, not just for the sake of the law, but for the sake of the technology actually finding its footing. Part of posting this is just giving myself the opportunity not to be afraid anymore and part is to while a lot less people are listening say that I’m willing to be a small voice advocating for the right thing in these markets.

It was sort of hard for me to find the courage to say this because of how scary it got, but I find it important to be part of a solution rather than through my fear being part of the problem by omission. I moved on over a year ago and have a normal job and life. I still care a lot about the users in these markets and still would like crypto to find its place in the world even if after knowing all of this I no longer feel excited to be a part. I’m hopeful that maybe at some point these learnings help other entrepreneurs going forward.

One interesting insight from playing chess with models is how our (human) minds have the ability to shortcut problems via intuition, whereas an AI needs to think, and think hard, about how to get there.

I’ve thought this for a while, but there are hints that what our minds do is very different than just produce words, but somehow we are able to very quickly produce actions that are out of distribution but directionally correct. There are many areas of life like this, but it’s worth considering vs listening to the AI doomers talk about how the AI will get better than us at everything because not everything is thinking in words.

Life is starting to get better again after this significant period of resetting but one thing I realized this week is how the online version of me has diverged from the old version of me and that I have some fear about showing up differently in different contexts. The person I was online three years ago is very different than the person I am now. When I was facing that, I realized the reality is that it’s just an opportunity for who I am now to be open and honest.

To understand that intro though I wanted to write a little bit about this story in case it helps someone either close to me or far away make a change that impacts their life like it impacted mine - life is too short to be as miserable as I was and if I can save even one person from that reality, then saying something is worth it. At this point everyone in my life who matters knows about my sobriety, so saying out loud really isn’t that big of a deal.

Drinking

My drinking went through this progression where it morphed slowly from something that was exciting, to a necessity, to something that almost killed me and I think sharing that might help other people in the same place feel less alone. I started when I was 24, which is late for most people. In my childhood drinking had been stigmatized and throughout college I largely stayed away from parties because I was pretty nerdy and thought that it would just hinder me professionally.

In early 2021 the first company I worked for went public and I had more money than any 24 year old should have reasonably had at the time (and had no idea what to do). My first thought was to move to NYC and “be a 20-something“ which meant that I started going out with friends and drinking. I got my first serious girlfriend and I felt like I had an avenue to be social. I had arrived and finally thought I could be myself

Then a bunch of bad things happened. I invested ~80% of my money in altcoins and risky startups in early 2022, which by the end of 2024 had basically vanished. The startup I started running that same year was failing hard, with investors I deeply respected onboard, and I had to lay off a core group of friends I had recruited to join me. I wasn’t ready to admit that failure. That year, 2023, was probably the worst of my life, and slowly that solution to being social became my solution to the fear I had of the failure I was experiencing. After this I kept trying to prove it wasn’t me and while building a few solid products and failing at a couple more shots on goal, staying in the arena until I hit the floor. I went from going out a couple of days a week to having a habit that became at least every night but started to bleed into lunches, random outings, plane rides, and wherever I could squeeze it in - my life became about the next time I could put some substance in my body to change the insecurity I felt inside.

I avoided that problem for a long time until things got pretty bad, worse than I would ever like to admit, but it was clear I needed to change something but I avoided that for a long time. In the meantime I kept prolonging that slow bottom because my solution was still working.

Real Solutions

On September 6th, 2024 I took the first real action towards getting sober which was getting dry. This is the date I took that daily habit to zero (although I slipped close to 9 months later briefly which I consider the last time I used anything to change my mind). I had told myself a bunch of times that I was “done“ but something on the night of the 5th really shifted something inside me and I decided I was done. In hindsight I think it was seeing someone else who was in a similar situation really trying and making some progress that inspired me to get there.

This started a whole process of not just willing myself not to use substances, but actually to begin a process of introspection that I can only describe as a spiritual experience that would lead me to change my attitude so dramatically towards life that I see myself as a wholly different person (much of this process has been published on this blog is about that under different wording!). It made me rethink and correct the record with whoever would listen, and to this day it makes the current version of myself willing to clean up the mistakes that the old me made and face the judgement that I thought others might have of me. For that I’m extremely grateful.

My solution was to self medicate my problem of the constant deep inadequacy I felt about myself. The places that led me caused me to hurt the people I was closest to which required a host of corrections over a long period of time. At this point I’m proud to say that I don’t hold any resentment and I don’t have anyone I’d be afraid to run into on the street because I went to everyone in my life and corrected those records - that in of itself is a miracle. Every day I wake up with some sense of gratitude for the small things in life and I don’t have the same desires for the things I was “chasing“ to try to fix my problem. Most of all I don’t think about substances ever anymore and because everyone in my life knows it’s virtually impossible to go back. It’s also why I’m not worried about talking about it here, because it’s not a secret.

The funny part of it is that life has changed a lot too - I don’t really care about status (that was more of an ego thing) and more important to me than anything has been helping other men going through the same thing which I spend time every week doing. In some ways “losing” that old life was the key to gaining a lot of peace that I probably would have spent a lifetime trying to get otherwise. I’ve worked to clear my side of the street, and while I know I can’t reach everyone I’m committed to listening if someone still feels like I owe them an explanation (if you’re reading this and still want something clarified I can always be reached at carl@carlcortright.com and I’m willing to talk). I still care about having a good life, but what I discovered was building that on the wrong foundation was the wrong path and in many ways I’m grateful to have had a clean slate to build on, even if that meant wiping some rubble away.

What I’ve found the deeper I get into it is that people don’t really make these changes unless they see examples of them working. I don’t have secrets anymore in life, and this has become an easy one for me just to give away so maybe if I’m lucky someone else can find something similar. For me all it took was a little openness and the willingness to be honest with myself. After that, things got a lot better, but it took me finding space to surrender what I couldn’t face for a very long time. I’d encourage anyone who wants that to make the decision to go find it and I’m always happy to talk with folks who will listen.

For this post - it’s one of many I’ve written. If you think it might be useful to someone in your life I’d love for you to share it with them directly but as with most things I write I don’t expect a ton of attention - somehow though it tends to get to the places that matter.

Is Claude Mass Psychosis Affecting Your Home?

Symptoms of Claude Mass Psychosis include:

• The uncontrollable need to tweet hourly about how Claude is “doing 100% of your work” while you sit in a dark room staring at a terminal.

• An unhealthy obsession with Claude Code and the belief that a CLI is your new best friend.

• The persistent, pseudo-philosophical urge to explain to anyone who will listen that Anthropic equity is actually just a call option on all future value within the light cone.

• Running Claude overnight to build complex products that literally no one—not even your mom—is ever going to use.

• Generating massive amounts of slopware that looks like an app but functions like a fever dream.

• Asking Claude to “handle your inbox” and promptly getting phished by an attacker because the model thought a “Limited Time Offer” was a high-priority stakeholder.

• Allowing Claude access to your iMessages, only for it to autonomously text every one of your ex-girlfriends pictures from your 2022 trip to Hawaii with the caption: “Thought you’d like to see these artifacts.”

If you or a loved one is suffering from one or many of these symptoms, you may be entitled to financial or emotional compensation. Contact 1-800-CLAWBAC to submit your claim today. Don’t let the LLM take your dignity along with your API credits.

In All Seriousness

I’ve been seeing a massive surge of Claude-related hype on X (Twitter) over the last few weeks—especially with the rise of CLAWDBOT and Claude Code. Curiosity finally got the better of me. Given the state of the market, I assumed most coding models had hit a plateau—they’re all basically the same, right?

But the discourse made it seem like Claude was different. People weren’t just calling it a helper; they were treating it like a magic tool that could autonomously submit PRs and ship perfect features while you slept.

That was anything but my experience.

Instead of “magic,” I found a deeply frustrating workflow. It was incredibly difficult to see the outputs being produced in real-time, reviewing code changes felt like a chore, and actually building something useful was an uphill battle. For people building real products, I don’t think Claude is that great of a tool. Maybe for someone building a small toy in their garage.

Why I’m Sticking with Cursor

While the “vibe coders” are letting Claude run wild in their terminals, I’ve found myself retreating back to Cursor for almost all of my actual engineering work.

For regular engineering, Cursor just feels better. It doesn’t try to be a “hands-off” agent that deletes your files when you aren’t looking; it stays in the flow of a standard development cycle.

• Real-time Feedback: I can see exactly what is being changed as it happens.

• Granular Review: Reviewing a diff in an IDE is infinitely more productive than squinting at terminal output or waiting for a bot to tell you it’s “finished.”

• Velocity with Control: It makes me significantly faster without stripping away the “engineering” part of the job.

Claude might be the viral star of the moment, but for shipping real code to production, I’ll take the IDE over the psychosis any day.

Finished this book last week and thought others might enjoy it. It seems very self-help-y but I liked the dialog format and also the philosophical underpinning. It’s written as a discussion between a philosopher and student about happiness and social relationships

It was the first time I’ve been exposed to Alfred Adler and his philosophy and framework. That part actually isn’t Japanese at all! Whether you agree or not, a framework that denies trauma, frames all problems as interpersonal problems, and roots happiness in service to community is a fascinating one that aligns with my understanding of the world that I’ve developed in the past 1.5 years.

If you like philosophy, especially in this dialog format, I highly recommend!

I’ve been thinking a lot recently about agentic systems and the shift in how we actually get work done. We’re entering a phase where AI agents aren’t just “chatbots.” They are starting to take over massive chunks of the workflows humans used to own end-to-end.

This shift changes the very foundation of how we build software. For decades, SaaS was built around Systems of Record. But the future? The future belongs to Systems of Action.

The Death of the Discrete Object

When you think about traditional SaaS, it’s centered around discrete objects. Think of a library: you have a book, a genre, and an author. The software is just a way to query those objects. It’s a database with a pretty interface.

There’s a lot of noise right now that Systems of Record are becoming “cheap” to build, and that the cost of this kind of software is going to zero. Maybe it will. But the real reason the old model is fading isn’t just cost; it’s utility. Users don’t just want to store data anymore; they want the data to do something.

The “Domino’s Pizza Tracker” for Work

While a System of Record is centered on objects, a System of Action is centered on timelines.

I like to describe it as the “Domino’s Pizza Tracker” for any unit of work. Whether a human is doing the task or an agent is doing the task, the system tracks the progression of that work in real time.

Behind the scenes, a developer sees this as a graph, specifically a directed semi-cyclic graph. Each node is an action:

• An LLM processing a request.

• A tool call to an external API.

• An agentic loop where the AI self-corrects.

• A “Human-in-the-Loop” moment where a person needs to sign off.

But the end user doesn’t need to see the “spaghetti” of the graph. To them, the “truth” of the system is just a clean, linear timeline of nodes visited. It’s the story of how the job got done.

Why This is the New Moat

This is where it gets fascinating: Systems of Action allow you to build proprietary IP into the execution of the job.

To build a great agentic system, you need incredibly detailed insight into the “Jobs to Be Done.” You are essentially compressing complex human workflows into a digital timeline. By owning the sequence of actions, you are building a deeper level of intelligence into the product than a simple database ever could.

The User Reality

There’s all this noise in the industry right now about “context graphs” and other technical buzzwords. Maybe that matters under the hood, but to the end user, it shouldn’t. The truth is that the system of action should just look like a timeline. It should be a transparent record of discrete events, human-driven or agent-driven, and the ability for the user to see that the whole agentic system is tracking everything.

We’re moving away from software that just sits there and waits for you to type. We’re building software that moves.

I’ve been aware of tools like Wispr Flow for a while (and even looked a bit at building here). This is a hot take, but not everything should be voice. For most short-form, keyboard is easier.

Long form my process has become this:

1. Use apple voice memos to dictate something long (3-10 minutes of speech) into a note

   1. At the beginning of the note, dictate instructions for what the LLM should do with the text (ie write this in my voice, no em-dashes)

2. copy transcript from apple voice memos to my clipboard, paste into my favorite LLM and let it rip

Not everything I’ve written in this time has been this way, but it’s for sure an efficient way to write well-formed posts, todos etc in my voice. The most common use cases I’ve used it for:

• Long form blog posts (2-5 pages)

• Long technical specs for cursor - turning them to .mds or long prompt for the LLM

• Thought out tasks for employees and coworkers

Shorter messages I’m still defaulting to typing - it’s not as much of a time-saver because your keyboard is always right there for up to a few sentences. Voice is a great way though to pound out work while in the car or on the go and have it waiting for you when you’re back at a laptop. Also voice memos are free and already built into your iphone, no expensive subscriptions.

Hope this idea helps someone else!

(ironically this post was not a voice memo)

That CEO had this saying: a 40 watt lightbulb can dimly light a room but a 40 watt laser can burn through steel. The engineer in me questioned the later statement (maybe thick cardboard, but steel is pretty strong), but the principle holds true: focus is what yields results.

The current hype wave around vibecoding reminded me of this idea in the past couple of weeks. Building businesses is actually fairly orthogonal to doing the coding work (which has always been reserved for the nerds), it just happens to be that the coding side of building companies was a hard requirement and used to be a high-bar. Your 10 claude code instances can’t sell the product or talk to customers, for that you need extreme focus, creativity, and resilience.

It’s very clear that there will be more software in the world, and that more broadly agentic harnesses will lead to the commoditization of services as we know them. Building and scaling companies is something very different though that requires creativity, agency, grit, and a lot product insight (and sometimes luck) to make work.