Yung #23 retweeted
🚨: Claude can now build your one-person business like Dan Koe’s $5M solo empire (for free).
Here are 5 Claude prompts that replace your business coach, content strategist, and offer architect.
(save for later)
Yung #23 retweeted
the most underrated Claude account on this app:
Most people think building an agent means writing code, but this one comes down to four folders and a few pasted prompts. If you know where each piece lives, you can set up the whole thing in about 10 minutes.
Start with the install. The terminal version is one line, npm i -g, and the desktop app and the VS Code extension are alternatives if you would rather click. Pick the one that fits how you already work.
The first file lives at ~/CLAUDE.md in your home folder. Claude reads it before every chat, so give it four headings: Role, Voice, Banned words, and Defaults. You do not have to write it yourself. Paste the prompt that asks Claude to build it from Boris Cherny's CLAUDE.md as a starting template, and answer its questions about your business, voice, banned words, and output defaults.
The second place is ~/.claude/projects/{project}/memory/. Tell Claude that whenever you correct it, it should save the correction as its own .md file there, prefixed feedback_, user_, project_, or reference_, with everything indexed in MEMORY.md. You correct it once, it saves the file, and it loads next time.
The third is ~/.claude/skills/{name}/SKILL.md. Describe a workflow by its trigger, inputs, and outputs, and ask Claude to wire in the connectors you need, like Notion, Gmail, or Drive. After that, /your-skill fires the whole thing from any chat instead of you retyping a 200-word prompt.
The fourth is ~/.claude/agents/, one .md file per specialist. Run a Strategist on Opus, a Builder on Sonnet, and a QA gate at 95 out of 100 that fails any work below the bar. Opus goes on the analyzing roles and Sonnet on the executing ones.
Last, make it run without you. A Claude Routine runs on Anthropic's cloud, not your laptop, so you can schedule it for 8am UK every day or every Monday and have the output drop into Notion.
Bookmark this before you start building and create the files in this order, because each one builds on the last.
Yung #23 retweeted
Been following Sandeep for four years now. My private investing framework is a lot closer to his (you can cross verify from my previous posts) but at his scale he’s a damn good money manager and you should go back to his tweets over the last few years and understand the timing and contrarian approach. You don’t even need to invest with him, just following his posts has huge alpha.
Yung #23 retweeted
the hottest job in tech right now is basically being good at hanging out
startups and vcs are hiring people with titles like ecosystem lead whose whole job is showing up in person. dinners, run clubs, coffee, the panel nobody wanted to go to. it sounds like a joke until you realize why
every company now has the same ai writing the same launch post, making the same video and sending the same cold email to the same inbox. marketing got infinitely cheap, which also made it kind of invisible. when everyone can automate the pitch, the pitch stops working
so the thing that cant be automated becomes the whole strategy. being in the room. remembering someones name. replying to a comment like a person and not like a growth tool
same thing is happening online. the accounts actually growing right now are weirdly manual. they answer people by hand, they show up in other peoples replies, they post things that clearly came from their actual week. its slower and it doesnt scale and thats exactly why it works
when i was building my old account to 5.3M, the internet mostly rewarded whoever could post the most. i think that era is ending. volume is free now. real attention to one specific person isnt
the funny part is sf spent a decade trying to automate every human interaction, and the most valuable skill in the city is turning out to be the one you learn at a dinner party
do the thing a bot could do. just do it yourself
Yung #23 retweeted
The biggest opportunities right now:
1. build for solving loneliness (the more AI floods everything, the more people crave real human connection, IRL and small social)
2. build for places with no cameras and no recording (being offline and unseen is turning into the new status symbol)
3. build for the crisis of young men. Millions of guys in their 20s feel completely lost with work, dating, and purpose. Whoever builds real brotherhood, mentorship, and an actual path forward wins a massive market (and helps a ton of people).
4. build for protecting people's brains (feeds are turning everyone's attention to mush, tools that protect your focus and mood are an easy sell)
5. build for the death of "everyone agrees" (you can find a chart or a podcast clip to prove any point now, people are starving for one source they actually trust)
6. build for day 2, not day 0. Anyone can launch an app in a weekend now. But how can you keep it running, fix the mess, and grow it for 3 years.
7. build for throwaway software (not everything needs to be a $20 a month subscription, tiny apps made for one trip, one wedding, or one group chat are coming)
8. build for people whose ego just got bruised by AI. Millions of smart people are realizing their job was mostly pattern matching. Help them figure out what they're good for next.
9. build for things that take effort on purpose (when everything is instant and free, nothing feels earned, people will pay for slowness and craft)
10. build for people who miss being told they're wrong. AI agrees with everything you say now. Real rooms where smart people actually push back on your ideas are becoming a luxury.
11. build for skin in the game. The internet is full of free takes and bots. Any platform where people have to put real money, real names, or real work behind what they say wins.
12. build for agents that need to spend money (they're getting virtual cards and budgets, someone builds the spend controls, fraud protection, receipts)
13. build for the end of fake email jobs (half of corporate America knows their job is theater, build the exit ramp for people who want to do real work)
14. build for the friend with great recommendations (nobody trusts Yelp reviews etc anymore because it's all bots and SEO, people will pay one obsessive person to just tell them where to eat and what to buy)
15. build for life after the chat box. Typing prompts already feels old. The best AI products won't look like chatbots at all, they'll just sit in the background and proactively handle things.
16. build for markets too small to matter before (500 lobster fishermen was never worth a team, now it's a real business if you can figure out what to build value to add to these fishermen lives!)
17. build for helpful without being creepy. AI is getting very personal very fast. Whoever figures out how to make it feel warm instead of weird owns consumer tech.
18. build for small private rooms (the public internet feels like an ad and a bot farm, all the good conversations and deals are moving into small invite-only groups)
19. build for someone taking the blame. AI can write the contract or read the scan, but a machine can't look you in the eye when it goes wrong. People still pay for a human on the hook.
20. build for learning that actually keeps up (a four year degree is way too slow for how fast things move now)
21. build for the anti-AI premium (as everything gets generated, human-made and unpolished become status symbols people pay up for)
note: more trends/ideas ideabrowser.com (free to sign up)
22. build for the return to the physical (screens fill with slop, people crave the real world, the hands on, the local, the analog)
23. build for the caregiving wave. The population is aging fast, tens of millions are caring for parents, and the whole burden is landing on families with no support.
24. build for finding things you didn't know to search for (algorithms just feed you more of what you clicked yesterday, people miss stumbling onto something totally different)
25. build for the housing and rootlessness problem (people can't afford to settle down, and the whole idea of a stable home base is up for grabs)
26. build for anti marketing (the slickest, most polished websites now look like AI slop or a scam, sometimes a plain text page from 1998 converts better because it feels like a real person built it)
27. build for agents that sit on hold for you (canceling a gym membership, fighting a medical bill, haggling with your internet provider, aint nobody got time for that)
28. build for software you actually own (people are exhausted from renting 30 different subscriptions every month, pay once and run it on your own machine is a massive wedge)
29. build for stuff that only works locally. The internet feels like one giant mall where every city has the exact same coffee shops and trends. Things that refuse to scale are suddenly cool again.
30. build for the 90% automated, 10% human sign-off model (clients don't actually care if AI did the heavy lifting, they just want one real expert to check the work and put their name on it)
31. build for infinite creative testing. Some brands are lighting money on fire on Meta because their ads die in 10 days. Build an automated pipeline that pumps out 100 fresh UGC and static ad variations a week based on what's actually converting in their ad account.
32. build for cold outreach that doesn't look like cold outreach. Mass blasting 50,000 people with "Hope this finds you well" is dead lol. Build an agent that watches for one specific trigger like a new VP hire or a broken checkout page, builds a custom teardown on the fly, and sends it before a human SDR even wakes up.
33. build for programmatic free tools instead of blog posts. Spin up 200 tiny, hyper-specific calculators, little apps and templates for one niche, rank them, and turn the traffic straight into conversions.
34. build for the food and toxin awakening (people are finally waking up to ultra processed food, microplastics, and why everyone feels sick and tired all the time)
35. build for the death of third places (there is almost nowhere left to just hang out without spending $50, which is why run clubs, saunas, and neighborhood clubs are blowing up)
36. build for people who can't retire at 65. Either they can't afford it or they're going to live to 95 and don't want to spend 30 years watching TV. The second act"market is huge.
37. build for the "undo" button for agents. Giving an AI access to your inbox, calendar, or bank account is still terrifying. Whoever makes it safe to let go of the wheel wins.
38. build for the sports betting and day trading hangover (a whole generation of young people are addicted to gambling on their phones and blowing up their bank accounts)
39. build for the death of the attention span. Smart adults can't even sit through a movie without checking their phone or finish a book anymore, and they're starting to hate themselves for it.
40. build for keeping marriages alive. Couples are stretched thin with work, kids, and money, and traditional therapy is $250 an hour with a waitlist. Anything that actually saves relationships is priceless.
41. build for people who don't own anything anymore. You rent your apartment, lease your car, stream your music, and subscribe to your software. Anything that helps regular people actually own an asset again wins.
KEEP BUILDING
🚨 BREAKING: WHY SPEED BEATS LOCATION IN THE AI RACE: IMAGINING JENSEN HUANG'S TAKE ON TESLA LEAVING TEXAS
🗣️When you are building at the scale Elon is operating—combining physical manufacturing, robotics, and massive AI supercomputing clusters—your headquarters is much more than an administrative mailing address; it is the center of gravity for your entire engineering ecosystem. Moving an operation of that magnitude out of Texas, especially after pouring so much energy into Austin’s Gigafactory and Terafab infrastructure, is an extraordinarily complex undertaking that impacts thousands of engineers and supply-chain partners. At the same time, Elon has always operated with a rare kind of first-principles urgency, and when he feels a region's regulatory or political environment is slowing down his velocity of innovation, he has shown he isn't afraid to pack up and rebuild elsewhere.
In the modern industrial era, speed of execution is the ultimate competitive advantage. Building next-generation autonomous systems and AI factories requires massive power infrastructure, rapid permitting, and deep alignment between private innovators and local leadership. When friction builds up in that equation—whether through shifting state policies or regulatory bottlenecks—a founder who thinks from first principles naturally looks at where they can move the fastest, even if it means uprooting a major corporate footprint.
Ultimately, what matters most in the AI and robotics race isn't the zip code on the building, but the speed at which you can deploy compute, attract world-class talent, and turn ideas into physical reality. Whether Tesla stays anchored in Texas or decides to plant its flag in a state like Florida, Elon’s superpower has always been his willingness to take bold, unconventional leaps to protect his companies' momentum. No matter where he sets up shop, the real story will always be the technology his teams are building.
Steelers Bengals Joe Burrow DK Metcalf Aaron Rodgers Cowboys
Chase Brown Dak Prescott 49ers Jerry Omar Khan 3 TDs
#氷渡香名江ついに実装 山形ユキオさん デアリングタクト ウルトラマンテオ 実刑判決 執行猶予 中田乃愛 ジャンポケ斉藤慎二 全曲サブスク解禁 NTTドコモ 実刑4年 全曲配信
Elon Musk relocating Tesla’s headquarters out of Texas feels less like a strategic business pivot and more like an impulsive rerun of his 2021 California exit, proving that no state can offer enough tax breaks or deregulation to satisfy a CEO who treats corporate infrastructure like a personal bargaining chip whenever local politics shift against him. Packing up a flagship operation—especially after pouring billions into Gigafactory Texas and turning Austin into a self-styled tech mecca—would create massive operational whiplash for thousands of employees while signaling to investors that Tesla’s long-term stability is permanently hostage to Musk’s latest political grievance.
Yung #23 retweeted
Follow him; he’ll make you money.
$spy Good morning everyone. Data is coming up. Its initial jobless. 740 should reject. Going to take a lotto puts just in case it drops. Domiant king 1 is way lower 707 unless it changes after open. Good bet into data.
Not a financial advice
#GEX #GammaExposure #spx
Yung #23 retweeted
Goldman out tonight warning stock market selloff is not over.
Asia likely agrees.
And so will FOMC soon.
Crash Check: Where We Stand
Options expiry was supposed to clear the decks. Instead it removed the last cushion. The S&P fell 3.7% to 6,910 and Nasdaq 100 futures fell 5.5%, finishing the week down 8.6% and 10.4%. Nvidia fell 14% to 125.53, and the neoclouds fell 12% to 18%. Dealer gamma fell 10% into the close, so there was nothing left to absorb the selling, and the market finished near the lows going into Thanksgiving week. VIX jumped 7.5 points to 35.9 and now sits 16% above three-month vol. One-day VIX hit 51, vol of vol 138, and one-month correlation 36, up from 11.8 a week ago. Every vol signal is now in crash territory. This is no longer a rotation out of crowded AI trades. Everything is being sold together.
Credit has joined in, but from the top of the market. IG widened 2.6bp, its biggest move of the week, and HY widened 13.7bp. Over the week HY is out 35bp and IG 6.4bp, so junk is keeping pace with investment grade, not outrunning it. The single-name CDS moves show the stress is in AI investment grade balance sheets. Nvidia’s CDS jumped 18%, CoreWeave widened 135bp, Oracle 21bp, Broadcom 11bp and Meta 6bp. The hyperscaler spread index rose another 9 points. Nvidia’s credit repricing matters because it has been the financier behind much of the AI buildout. The Helios data center bond fell to 89.5, and Blue Owl made another new low. Gold fell 4.6%, and 9.5% on the week, and Bitcoin fell 4.2% to 58,930. Selling gold and Bitcoin alongside stocks is a sign of investors raising cash wherever they can.
What’s still holding is bonds and funding. The 2-year fell 11.5bp today and almost 20bp on the week. Half the December hike pricing has come out of the curve, and short-dated inflation expectations are collapsing, so the market is starting to price a Fed response. The yen strengthened as carry trades came off, but USD/JPY didn’t break 160. China’s currency firmed, and repo is calm. Our crash scorecard went from 4 red to 6 this week. The difference between a violent deleveraging and a credit event now comes down to three things: whether high yield starts outrunning investment grade, whether the Helios bond breaks 85, and whether USD/JPY breaks 160. None of them has happened yet. If they hold, the bond rally and a repricing of the Fed are the way out.
Yung #23 retweeted
PETER LYNCH EXPLAINS EXACTLY WHAT TO DO WHEN THE STOCK MARKET GOES DOWN.
THIS IS A MUST-WATCH FOR EVERY SERIOUS INVESTOR. ❌🐻
Yung #23 retweeted
7. The Executive Function Externalizer
Prompt: "My brain is full of 'Open Loops.' I will dump everything I'm worried about below. Categorize these into 'Now,' 'Later,' and 'Trash,' and then write a 1-sentence 'Actionable Next Step' for only the 'Now' items."
Yung #23 retweeted
I hope you found it helpful
Join my newsletter and get more like this
Which one hits closest to home? 1 to 7.
its FREE
aiinpublic.com
Yung #23 retweeted
🚨 BREAKING: Claude has a hidden ADHD Executive Function Mode.
You can use it to hack your brain’s dopamine and finish a week’s worth of work in 4 hours.
Here are 7 prompts to access it:↓
Yung #23 retweeted
One of the most overlooked reasons men’s testosterone is so low (and nobody talks about it):
How they approach challenges
Whether they push to achieve things (or avoid them)
And how they handle losing
I saw it firsthand with the Giants
We ran regular blood draws on the entire roster during the season
We lost a lot those years (A LOT)
And not everybody’s body handled it the same way
Some guys held up
Others trended the wrong way (testosterone down, cortisol up)
And when that happens, injury risk goes up
The difference wasn’t just training or sleep
It was how they handled losing
The research backs it up:
Testosterone can rise BEFORE competition, mostly when it matters to you and you believe you can win
After a loss you can do 1 of 2 things:
1. Shut down and accept defeat => testosterone drops
2. See it as a challenge you can learn from => it can actually go UP
Now look at a lot of men today
-Afraid to lose, so they never compete
-Don’t push or challenge themselves
-Play the victim when things go wrong
-Afraid of rejection so they don’t even get in the game
-Give up too easily
-Stuck in jobs or situations where they feel they have no control
-Emasculated at home/work/in their inner circle
That’s a losing mindset, every single day
And even if your nutrition, training and recovery are dialed in, if your mindset is weak, your body responds physiologically to that too
It’s not the only reason testosterone is dropping across men at all ages (body fat, sleep and inactivity, stress/anxiety, nutrient deficiencies are huge)
But it’s the one nobody really talks about
You can reverse this issue by:
-Doing hard things/challenging yourself regularly (get outside your comfort zone)
-Setting goals that actually matter to you and taking steps towards them
-When/if you lose, reframe it by learning and going again
Yung #23 retweeted
if you’re building agents for the enterprise and not following this account, you’re not serious
The better the harness, the better the business.
By harness I mean everything you build around the model.
It tells the agent where to get an answer, what it’s allowed to do and when to hand the work to a person. It also includes the tests you run before you change any of those rules.
That matters for two reasons.
#1 What an answer costs.
Say your agent gets 1,000 questions a day. If you can write a rule that answers 700 of them, only 300 need to go to the model. If each question costs about the same, that cuts the model bill by roughly 70%.
The hard part is knowing which 700. For that, you need somebody who does the work and can tell you when the usual rule is not applicable (exceptions).
On a logistics platform we rebuilt, AI cost about $200 per developer per month. What took time was figuring out how the old system calculated customers’ bills and which rules we needed to keep.
#2 What the company gets to keep.
Take the patient-billing voice agent we built for a US healthtech startup. It can give a patient the correct balance and still handle the call badly.
> Did it verify who was on the phone first?
> If the patient disputed the charge, did it hand the call to staff?
> If it scheduled a follow-up, did it check non-working hours when the message actually went out?
Those decisions are part of the harness. The system ran 13,650 tests on every pull request. In production, it handled 61,246 calls, and about 97% of patient conversations finished without a human stepping in.
The company-specific IP is clearest in the exceptions.
When an experienced billing lead explains why two calls that sound alike need different handling, you can turn that distinction into a rule and save both cases as tests.
Now the next engineer can change the workflow, or try a different model, and check whether it still makes the call the billing lead would make.
Your competitor can rent the same model, but they still have to learn which exceptions matter and what to do about each one.
If you run a software company adding AI this year, I’d put the budget there first. Sit with the people who handle the exceptions. Write down how they decide. Give the model the work that still needs judgment.
Yung #23 retweeted
Wow. @TraderMorin just leaked his most profitable trading patterns to make a f*ck ton of money...
I feel bad for whoever doesn't like/bookmark this:
Yung #23 retweeted
Passive income is the path to wealth and freedom.
Below are 6 passive income ideas for you:
Yung #23 retweeted
Follow this account if you want to learn really useful things about AI
Every post is very useful.
































