Max Kotin

41 posts

Max Kotin

Max Kotin

@kotinmaks

https://t.co/LjD8rUDfag creator 👨🏻‍💻

Berlin, Germany Katılım Mayıs 2023
105 Takip Edilen45 Takipçiler
Max Kotin
Max Kotin@kotinmaks·
@dhh So, everything gets paused - work, family, kids - when a new DHH interview drops! Please tell us more about your current take on AI. Considering your advocacy for typing everything by hand, it's fascinating how much has changed in just 3-4 months...
English
0
0
2
263
Max Kotin
Max Kotin@kotinmaks·
@pmitu and thus it becomes a second job :)
English
0
0
0
3
Paul Mit
Paul Mit@pmitu·
How to get your first 1,000 followers on 𝕏: • 1 tweet per day • 30 meaningful comments per day • 30 new connections with interesting people • 30 small talks in DMs No magic.
English
129
10
212
9.1K
Max Kotin
Max Kotin@kotinmaks·
@tomhacks The problem with this approach is that Ai takes the instruction to be a jerk literally and starts flagging things that are totally fine - and I don't know what's worse
English
0
0
0
29
Tom Siwik
Tom Siwik@tomhacks·
You can break your whole delusion of this sycophantic agent just by telling it to review like an adversary with 100% scrutiny and no mercy. However it should evaluate key finding still so you have a tiny straw to cling on to and fight against it. You keep it in check and your sanity at bay. If I hear the AI telling me "great instinct, good catch, sharp thinking" it's always time to bring out this adversary gun and shoot myself in the foot. It works. Easy fix.
Mo Bitar@atmoio

AI is making CEOs delusional

English
7
0
28
7.3K
Max Kotin
Max Kotin@kotinmaks·
@atmoio Ai is making everyone delusional! To be fair, it might have a positive effect too, majority of people need a confidence boost to stop moping and start doing something
English
2
0
10
2K
Mo Bitar
Mo Bitar@atmoio·
AI is making CEOs delusional
Indonesia
1K
2.6K
19.1K
2.8M
Max Kotin
Max Kotin@kotinmaks·
@dhh 1. AI can repackage existing knowledge well 2. AI can imitate your style - once you have one 3. A celebrity can post anything, it'll still be read, no matter the quality 4. "here's the kicker" is overused by AI, so we might be looking at AI-generated follow-up :)
English
0
1
0
32
DHH
DHH@dhh·
I've written a version of this rant several times, but I didn't write this version. This prompt did: "Write a 6 paragraph essay in the style of DHH about why microservice architectures are bad for small teams." I followed up with 2x "Make it more polemic", but I didn't change a comma. The emdashes gave it away for some, but without those, I think even fewer would have been able to tell. And here's the kicker: It's actually pretty good? Take this point: "Instead of reasoning about code, teams reason about failure modes, retries, timeouts, message queues, and versioned payloads. The cognitive load compounds with every new service." Spot on, nicely framed! What does that mean? Is AI still slop when it makes good points? Or when it produces an essay that resonates with thousands of people in just a few hours? I've locked the tweet, because I do feel ambivalent about humans unwittingly interacting with AI writing, but why do we? It's not at all clear this isn't just a transitionary phase, like when it felt scary for most to enter this credit card on the early internet. Here's the the full interaction with the versions produced before prompting for "more polemic": chatgpt.com/share/6939aaf0…
DHH@dhh

Microservices is the software industry’s most successful confidence scam. It convinces small teams that they are “thinking big” while systematically destroying their ability to move at all. It flatters ambition by weaponizing insecurity: if you’re not running a constellation of services, are you even a real company? Never mind that this architecture was invented to cope with organizational dysfunction at planetary scale. Now it’s being prescribed to teams that still share a Slack channel and a lunch table. Small teams run on shared context. That is their superpower. Everyone can reason end-to-end. Everyone can change anything. Microservices vaporize that advantage on contact. They replace shared understanding with distributed ignorance. No one owns the whole anymore. Everyone owns a shard. The system becomes something that merely happens to the team, rather than something the team actively understands. This isn’t sophistication. It’s abdication. Then comes the operational farce. Each service demands its own pipeline, secrets, alerts, metrics, dashboards, permissions, backups, and rituals of appeasement. You don’t “deploy” anymore—you synchronize a fleet. One bug now requires a multi-service autopsy. A feature release becomes a coordination exercise across artificial borders you invented for no reason. You didn’t simplify your system. You shattered it and called the debris “architecture.” Microservices also lock incompetence in amber. You are forced to define APIs before you understand your own business. Guesses become contracts. Bad ideas become permanent dependencies. Every early mistake metastasizes through the network. In a monolith, wrong thinking is corrected with a refactor. In microservices, wrong thinking becomes infrastructure. You don’t just regret it—you host it, version it, and monitor it. The claim that monoliths don’t scale is one of the dumbest lies in modern engineering folklore. What doesn’t scale is chaos. What doesn’t scale is process cosplay. What doesn’t scale is pretending you’re Netflix while shipping a glorified CRUD app. Monoliths scale just fine when teams have discipline, tests, and restraint. But restraint isn’t fashionable, and boring doesn’t make conference talks. Microservices for small teams is not a technical mistake—it is a philosophical failure. It announces, loudly, that the team does not trust itself to understand its own system. It replaces accountability with protocol and momentum with middleware. You don’t get “future proofing.” You get permanent drag. And by the time you finally earn the scale that might justify this circus, your speed, your clarity, and your product instincts will already be gone.

English
152
65
1.2K
184.6K
Vova Kras
Vova Kras@vovaflame·
I’ve been waiting for years for Apple to Release the todo app… My patience ran out and I did it myself lol
English
1
0
13
685
Paul Mit
Paul Mit@pmitu·
Scale from $0 to $10k MRR I’ll help you launch in 22 steps The full guide to get real $ traction Reply with “+” and I’ll send you the guide
Paul Mit tweet media
English
109
6
109
7.1K
Roman Buzko
Roman Buzko@roman_buzko·
Ever wondered where to set up a company for your next project? Delaware, Texas, or maybe offshore — like the UAE or BVI? We’ve got you. We at @Skala_io just dropped a comprehensive guide covering the top startup jurisdictions. The guide is interactive and comes with handy filters — from the usual (General, Crypto, AI, Solopreneurs, GameDev, Space, SPV, Asset Holding) to the truly useful ones, like Elon Fanbois or Zero Taxes. Links below 👇
English
2
4
24
754
Max Kotin
Max Kotin@kotinmaks·
@vovaflame so you can only add tasks and mark them done? that's it? :)
English
1
0
0
78
Max Kotin
Max Kotin@kotinmaks·
@pmitu ...reframing the definition of "fullstack" :)
English
1
0
1
21
Paul Mit
Paul Mit@pmitu·
🧑‍💻 If you're a developer who doesn't understand marketing. 👨‍💼 Find a marketer who doesn't know how to code. → now you have a fullstack team to conquer the market. That's it.
English
14
3
53
1.9K
Max Kotin
Max Kotin@kotinmaks·
@pmitu well, there is some landing page, it's just no finished! :)
English
1
0
1
120
Paul Mit
Paul Mit@pmitu·
hey builders and #buildinpublic We continue to work on improving the new AI product in a consistent manner: ✳️ Passed 500€ revenue ✳️ Already several renewals ✳️ The first client with ‘3rd paid subscription’ 🤷‍♂️ Still no landing page (in dev now) Work is in full swing 🏄
Paul Mit tweet media
English
2
0
21
687
Max Kotin
Max Kotin@kotinmaks·
@pmitu good vibes! (should be watched with sound on)
English
1
0
1
77
Paul Mit
Paul Mit@pmitu·
While the landing page is in the middle of development I created a Notion page with the content that was generated in our new AI app. Check ‘em out: bit.ly/AI_posts Wanna try beta? Please dm me 🔊 And turn up the volume on the video.
English
10
0
37
1.8K
Paul Mit
Paul Mit@pmitu·
I can't get past the fact that more and more professionals are using our AI app to create cool content by simply talking with AI-interviewer 💬 So how not to feature these great people on the main hero section of our upcoming landing page? Excited to be in such a good company. And excited to build the future of digital communications—welcome to 2025 😌
English
3
0
33
1.9K
Paul Mit
Paul Mit@pmitu·
Our new AI product keeps growing 🥳 So glad to have new customers joining us! It is important for me to get the product to market as early as possible. (even before launching landing page and announcements) Why? 🕊 Quick feedback. 🌿 First early adopters (#buildinpublic) 👨‍💻 Defining who the ‘power users’ are. 🥏 Not making the mistake of long development (no market need). P.S. Our AI tool helps professionals create awesome content for Twitter/LinkedIn just by talking to it. Use your voice and ideas. The rest is up to us!
Paul Mit tweet media
English
12
0
45
1.7K
Max Kotin
Max Kotin@kotinmaks·
@alexeykiryanov sometimes there is no choice, actually; sometimes it's a high risk-high reward kind of a situation, when you expect to cash out before everything falls apart
English
0
0
1
29
Alexey Kiryanov
Alexey Kiryanov@alexeykiryanov·
I can’t take someone seriously when they’re building a business in a dictatorship. On paper, everything looks great — funding, empty markets, tons of opportunities. But business is about risk and long-term thinking. If someone’s overly optimistic in those places, it feels like they’re missing something. Sure, you can make money, but what’s the point if you can’t even use it or take it out?
English
1
0
9
374
Paul Mit
Paul Mit@pmitu·
What kind of AI product are we developing? 🧬 Building a personal brand and driving LinikedIn/Twitter: Unclear. Difficult. Demotivating…… ✅ We've made an AI buddy that you can just talk to. Have pleasant 1-on-1 voice conversations. And get ready-made posts on LinkedIn. Say NO to 'AI generated shit' 💩 We get your thoughts, your ideas, your vision, your expertise directly from head 🧠 → ready to be published on LinkedIn. Easy. 50 people have already successfully tested our product. (total views on all posts >50,000, and 500 live comments under them) Want to try the beta version at -70% discount off? dm me
Paul Mit tweet media
English
2
0
18
773
Alexey Kiryanov
Alexey Kiryanov@alexeykiryanov·
In a chat yesterday, someone asked, “How do I find a partner as committed and reliable as I am when so few seem motivated?” The real question is: — Are you frustrated because people aren’t how you expect? — Or have you accepted that the world is imperfect and learned to work with it? I find it more productive to understand reality and build from there. What’s your take? #fridaypost
English
1
0
16
300
Paul Mit
Paul Mit@pmitu·
First revenue 🎉 The first paying user of our new AI product. We released monetisation yesterday (after 'private beta' mode). First milestone is very important #buildinpublic Step by step.
Paul Mit tweet media
English
21
0
64
2.1K