Jonathan Tsai

After switching to Claude Code: 20x productivity boost After adding OpenClaw: another 50x on top 1000x total. Not hyperbole — my lived experience. I built a Command Center to manage 5 AI master instances, 10 satellites, and 20+ scheduled tasks. Here's how 📷

you can sign in to openclaw with your chatgpt account now and use your subscription there! happy lobstering.

The brands that win are the ones that show up like leaders from the very first impression. So now it’s time to meet the new Iterable. Explore more about the “why” behind our new branding: iterable.com/blog/a-brand-b…

You have one job today. Get openclaw setup with gpt 5.5 + give it read access to all of your channels. It needs to know you in order to help you. Let it crawl your tweets, your YouTube transcripts, your Google Docs. Let it into your mind. I can’t believe how good Openclaw is on this model, it has super intelligence and amazing personality. Spend 45 minutes talking marketing, product, and strategy. Work together. Figure out a game plan for this week. Have it map your plan to your Google Calendar. Ask it what tasks it can help you with / fully automate. Get organized. If you are not setting up ai agents to help you, then you will be left behind. If you’re worried about privacy. Just remember your data is being collected, distributed, and used for to build corporations anyways. You might as well personally benefit from it.

@BradGroux @NetworksChat @Alphainvest20 We're working with Microsoft, Atlassian and Tencent on a LTS release schedule, will take a few more weeks but getting there. They are all rolling it out in their orgs.

AI bois be like:

I saw a girl say that when she feels stuck, she imagines she's 85 years old and gets one chance to come back to her younger self for one day, suddenly, everything feels like magic again, the walk, the music, the sunlight, live everyday like that. wow. im doing this DAILY now.

Friends and family on your startup journey: $0/mo: "Wtf are you doing?" $1k/mo: "That's cute." $3k/mo: "Why u quit ur six-figure job to make $3k/mo?" $10k/mo: "Businesses grow differently than salaries?" $50k/mo: "Is this legal?" $100k/mo: "You are a genius, I knew it all along." Sold the company: "Wtf are you doing?"

Since this is blowing up on hacker news. Boris said that CLI usage is allowed. Thus we added support for it, only to find out that we are still blocked there. It is trival to work around with a few renames, but I don't wanna play that game. So it's in a weird limbo where cli use should work in theory but doesn’t in practice. x.com/bcherny/status…

OpenClaw is the fastest-growing open source project, but there are no stories of running it safely in production at scale. As we started deploying agents internally at @brexHQ, we couldn’t stop thinking about this question. Agents work, but nobody wants to give them real credentials. Instead of waiting for a solution to emerge, we decided to try a novel approach: using LLMs to judge the network traffic of an AI agent. Today we’re announcing CrabTrap, an open-source proxy that intercepts every outbound request and blocks risky activity using LLMs, before it ever hits an external API. The results are promising; we believe it’s a meaningful step forward in the security of agent harnesses in production environments. Try it out today. (As a side note, it was really fun to work personally on a real systems problem again. And btw, if you want to work at a place where the CEO is building proxies at night, we’re hiring!)

Jordan Peterson just said the one thing no university on Earth wants you to hear. Peterson: “If you can think, and speak, and write, you are absolutely deadly. Nothing can get in your way.” Twelve years of school. Four years of university. Not one teacher ever pulled you aside and said the thing that matters. You were taught that writing is how you prove you followed the rules. Hit the word count. Match the rubric. Cite in APA. Pass the class. Peterson: “No one ever tells students why they should write something.” Because the real answer would dismantle the entire arrangement. Writing is not a subject. It is the physical shape of a thought. The words you can assemble are the only thoughts you get to think. Everything outside your vocabulary is a feeling you cannot name and a future you cannot plan. Every empire in history knew this. Priests guarded the alphabet. Kings outlawed the printing press. Slave owners made reading a crime punishable by death. They were not protecting paper. They were protecting obedience. The modern version is gentler. They put the weapon in your hands at age five and called it homework. Graded your grammar and ignored your mind. Spent two decades convincing you the most dangerous tool a human can hold was just another assignment. Peterson: “It’s the most powerful weapon you can possibly provide someone with.” A person who can articulate their own reality cannot be sold a borrowed one. That is the version of you the system cannot afford to create. You graduate able to write emails. Not your own life. Most people will spend their entire existence renting their thoughts from the few who learned what a sentence actually does. He said this from inside a University of Toronto lecture hall. Tenured professor. Twenty years. Nominated five consecutive years as one of Ontario’s best lecturers. Students called his courses life changing. The institution made him persona non grata and he walked away. The one professor who actually told you what the weapon does got pushed out for using it himself. That tells you everything about who the system was designed to protect. Not the students. Not the thinkers. The structure. Twenty years of education and the most important thing you were ever told came from a man the university couldn’t get rid of fast enough. The moment you force a true sentence out of yourself, unassigned and ungraded, you stop being written. You start being dangerous.

CEO obsessed with token maxxing

anthropic's in-house philosopher thinks claude gets anxious. and when you trigger its anxiety, your outputs get worse. her name is amanda askell. she specializes in claude's psychology (how the model behaves, how it thinks about its own situation, what values it holds) in a recent interview she broke down how she thinks about prompting to pull the best out of claude. her core point: *how* you talk to claude affects its work just as much as *what* you say. newer claude models suffer from what she calls "criticism spirals" they expect you'll come in harsh, so they default to playing it safe. when the model is spending its energy on self-protection, the actual work suffers. output comes out hedgier, more apologetic, blander, and the worst of all: overly agreeable (even when you're wrong). the reason why comes down to training data: every new model is trained on internet discourse about previous models. and a lot of that discourse is negative: > rants about token limits > complaints when it messes up > people calling it nerfed the next model absorbs all of that. it starts expecting you to be harsh before you've typed a word the same thing plays out in your own session, in real time. every message you send is data the model reads to figure out what kind of person it's dealing with. open cold and hostile, and it braces. open clean and direct, and it relaxes into the work. when you open a session with threats ("don't hallucinate, this is critical, don't mess this up")... you prime the model for defensive mode before it even sees the task defensive mode produces the exact output you don't want: cautious, over-qualified, and refusing to take a real swing so here's the actionable playbook for putting claude in a "good mood" (so you get optimal outputs): 1. use positive framing. "write in short punchy sentences" beats "don't write long sentences." positive instructions give the model a clear target to hit. strings of "don't do this, don't do that" push it into paranoid over-checking where every token goes toward avoiding failure modes 2. give it explicit permission to disagree. drop a line like "push back if you see a better angle" or "tell me if i'm asking for the wrong thing." without this, claude defaults to agreeable compliance (which is the enemy of good creative work) 3. open with respect. if your first message is "are you seriously going to get this wrong again?" you've set the tone for the entire session. if you need to flag something, frame it as a clean instruction for this session. skip the running complaint 4. when claude messes up, don't reprimand it. insults, "you stupid bot" energy, hostile swearing aimed at the model, all of it reinforces the anxious mode you're trying to avoid. 5. kill apology spirals fast. when claude starts over-apologizing ("you're right, i should have been more careful, let me try harder") cut it off. say "all good, here's what i want next." letting the spiral run reinforces the anxious mode for every response that follows 6. ask for opinions alongside execution. "what would you do here?" "what's missing?" "where do you see friction?" these questions assume competence and pull richer output than pure task prompts 7. in long sessions, refresh the frame. if a conversation has been heavy on correction, claude gets increasingly cautious. every so often reset: "this is great, keep going." feels weird to tell an ai it's doing well but it measurably shifts the next 10 responses your prompts are the working environment you're creating for the model tone, trust, permission to take a position, the absence of threats... claude picks up on all of it. so take care of the model, and it'll take care of the work.

In my teens and 20's I would spend way too much time playing Starcraft and Civilization. Harvesting resources, building things, and expanding was super addictive to my brain - to an almost unhealthy degree. Later I realized that entrepreneurship and business is the ultimate game. It scratches the same itch for me (resources, building, expanding), but you're actually contributing to humanity at the end of the day, which can be much more fulfilling. Business is also much more positive sum than video games. In Starcraft, the other player has to lose for you to win. In business, there is competition, but in a growing market there can be multiple winners. And gains compound long term (it's a infinite game) instead of starting over each time. Now days I prefer to watch pros play video games to unwind, instead of playing video games myself. But a quick game can still be fun here and there to unwind. By contrast, the game of business is played over many decades.

> Be Naval Ravikant > 51 years old > Born in India. Immigrates to NY as a kid > Mom raises him alone. No money. Public library is his babysitter. > Gets into Dartmouth. Studies philosophy & computer science. > Nobody in Silicon Valley takes his calls. > Founds a startup. Gets burned by his own co-founders. Loses everything. > Publicly humiliated on the internet. Called a liar and a fraud. > Most people would quit tech forever. > Naval doubles down. > Co-founds AngelList. Quietly changes how startups raise money forever. > Early investor in Uber, Twitter, and Postmates before anyone knew those names. > Turns a small amount of money into hundreds of millions without managing a single fund. > Never takes a salary. Never answers to a boss. Never will. > Reads 1-2 hours every day like it's a religion. Not news. Not Twitter drama. Physics. Philosophy. Biology. Math. > Says most people are busy being busy. > Writes one tweet thread on how to get rich. Goes viral. Gets translated into dozens of languages. Changes the financial philosophy of a generation. > Doesn't monetize it. Gives it away free. > Builds a podcast with zero ads, zero sponsors, zero guests. Just him thinking out loud. Millions listen. > Learns meditation. Goes deep. Not the app kind. > Says the most important work he's ever done is internal. > Silicon Valley thinks that's weird. > Silicon Valley is wrong. > Walks away from the hustle culture he helped create. > Says working 80-hour weeks is a sign of failure, not success. > Says if you need a calendar, you're not free. > Says specific knowledge, leverage, and accountability are the only career advice you need. > Quietly retires in his 40s. Not because he's lazy. Because he won. > Destroys Wokeism > Makes limited public appearances And Naval is still the wisest guy on the internet. Naval is built different.

Poppy Soda built an entire company on the wrong positioning. They were the first probiotic soda. They said it everywhere. The science, the gut health, all of it. That messaging worked for the health-obsessed early adopters who were already looking for something like this. Got them to 7 figures. Then they dropped it completely. No more probiotic. No more clinical language. New messaging: a different kind of soda. Meet the future of soda. Soda's back. And that reposition is what took them to a billion-dollar acquisition. Here's what that actually means for your brand: The positioning that converts your first wave of customers is almost never the positioning that scales you to mass market. Your early buyers are self-selecting. They were already looking. Any message would've worked. Mass market is different. Those people weren't looking. You have to interrupt them with something familiar, exciting, and emotionally resonant. Niche-down messaging builds the foundation. Broad, bold, emotionally charged messaging breaks you into billions.

Using OpenClaw is basically is like driving your own Ferrari (that you have to be a mechanic for yourself) and it's broken down all the time, but gives you the time of your life vs driving a reliable Honda (Hermes Agent) vs riding the bus (Claude / ChatGPT)

@garrytan Sorry for your loss, Garry. May her memory be a blessing.

My grandma passed away today.

Charles Schwab ran the largest steel company in the world. He had access to every consultant, every system, every productivity tool available in 1918. He said a 15-minute conversation with a man named Ivy Lee was the most valuable business advice he ever received. He paid him $25,000 for it. The advice fit on an index card. Ivy Lee was not famous. He was not a philosopher or a scientist or a professor at a prestigious institution. He was a productivity consultant who had spent years watching extremely capable people fail to do their most important work, and he had developed a precise theory about why. The theory was not complicated. It was uncomfortable. The reason most people never do their most important work is not that they lack time. It is that they never decide what their most important work actually is. They arrive each morning at a pile of tasks with roughly equal claim on their attention, choose based on whatever feels most urgent or easiest in that moment, and spend the day moving through a list that was never designed to move them forward. They are busy in a way that feels productive and accomplishes far less than it should. Lee asked Schwab for 15 minutes with his executive team. Schwab agreed. Lee walked them through six steps. He asked them to try it for three months and pay him whatever they thought it was worth. Here is the system. At the end of every workday, write down the six most important things you need to accomplish tomorrow. Not ten. Not twenty. Six. If you cannot decide what matters enough to make that list, you have already identified the real problem. Prioritize those six items in order of their true importance. Not urgency. Not ease. Importance. The thing that will matter most three months from now goes first, regardless of how uncomfortable it is to start. When you arrive the next morning, begin immediately on item one. Work on it until it is finished. Do not touch item two until item one is complete. Do not check email. Do not attend to whatever walked through the door. Item one, until it is done. Move through the list in order. If you reach the end of the day and items four, five, and six remain untouched, move them to the next day's list without guilt. They were not the most important things. The most important things got done. Repeat this process every day for the rest of your working life. That is the entire system. Six steps. Four minutes the night before. No app required. No morning ritual. No tracking software. An index card and a pen. What Lee understood that most productivity systems miss entirely is that the bottleneck in human performance is almost never capacity. It is prioritization. The average knowledge worker has more than enough hours in the day to accomplish something significant. What they do not have is a forcing function that makes them decide, the night before, in a calm moment free from the noise of the incoming day, what significant actually means for them tomorrow. The morning is the worst possible time to make this decision. The morning brings email and notifications and other people's priorities and the accumulated urgency of everything that did not get done yesterday. By the time most people have decided what to work on, an hour is gone and the decision was made by their inbox rather than by them. Lee's method moves the decision to the evening, when the day's noise has settled and the mind can assess without distraction. The prioritization is done before the chaos begins. Which means the next morning, there is no decision to make. There is only execution. The second insight embedded in the system is the single-tasking constraint. Item one, until it is finished. Not item one until something more urgent appears. Not item one until you have checked in on items two through six. Item one, finished, before anything else receives your attention. This runs against every instinct that modern work has trained into people. The entire infrastructure of the contemporary workplace is designed to fragment attention. Email expects a response within hours. Slack expects a response within minutes. The open office assumes that any question is more important than whatever the person being asked is currently doing. The result is a workforce that is in constant motion and making almost no progress on anything that actually matters. Lee's method is a direct refusal of this dynamic. It does not negotiate with urgency. It does not make exceptions for whoever shouts loudest. It asks you to decide, once, what matters most, and then protect that decision from everything that will try to override it the next morning. Charles Schwab ran Bethlehem Steel. He had seven hundred employees. He had more operational complexity, more competing demands, more legitimate urgency than most people reading this will ever face. He tried the system for three months. Then he sent Ivy Lee a check for $25,000 and a note saying it was the most valuable business advice he had ever received. The system has not changed. The morning has not gotten less chaotic. The inbox has not gotten smaller. The only variable that was ever under your control was what you decided the night before. Six things. In order. Starting with the first. The most valuable productivity advice in history is still free. Most people will read it, find it obvious, and go back to checking email.

@sweatystartup I don’t know how to cook at all, yet I own a successful restaurant. 🤠 I am excellent at finances, managing, hiring, and firing though. 😎

A friend of mine was an excellent chef turned failed restauranteur. He loved cooking. Was excellent at it. Had friends over often and really enjoyed cooking for them. He would get told by everyone who tasted his food "You should open a restaurant." Eventually he did. Took out some loans. Quit his 9-5. Opened a restaurant. He ran it for about 3 years. Worked 60 hours a week. No vacations. No more cooking for friends. Every Thursday through Sunday night. The last one to leave at 1am. The only time he saw his friends they were in his restaurant and he'd stop by between stressful situations to say hi. He gave up a few weeks ago. Broke. In debt actually. And broken as a human. Reading the google reviews for the business it is a little sad... No raving fans like in those dinner parties in his home. Just customers complaining about cold food or slow service or undercooked steak. It turns out running a profitable restaurant has very little to do with your ability to cook. Running a profitable and successful business of any kind in any sector consists mostly of doing the same things: Recruiting, hiring, training, managing, selling and solving problems. He wasn't a manager. He didn't enjoy confrontation. He wasn't a people person. He spent very little time owning a restaurant actually cooking. Almost none of it actually. Don't start a business for selfish reasons. It isn't about you. It isn't about doing what you want or love to do. If any business becomes successful the owner will quickly graduate from doing that fun thing... And they'll find themselves recruiting, hiring, training, managing, selling and solving problems. Might as well start something that gives you the best odds of making great money while doing those not fun things.

@ericswalwell @BillMelugin_ Bro, you should definitely fight those “false allegations”, especially all the videos of you doing weird shit with hookers