mattOS ✌️

16.9K posts

mattOS ✌️ banner
mattOS ✌️

mattOS ✌️

@matt_dot_sol

Anything But Corporate | Building @bvrstco and @NOMNOMMARKETS

NY Katılım Kasım 2010
1.7K Takip Edilen6.3K Takipçiler
Sabitlenmiş Tweet
mattOS ✌️
mattOS ✌️@matt_dot_sol·
On Thursday I got a message from a warm lead for a rapid turnaround contract. They were a marketing agency helping a client create a "surrealism-inspired" proposal for a big ticket event that would net them 6-7 figures long term. So they came to me and said "let's turn this pdf into a legendary web experience, but deadline is Sunday" The big problem: too many ideas and only 2 days to execute After spending hours storyboarding, digging into animation libraries, and prototyping, the fear of missing the deadline really set in. So we pivoted from a custom NextJS build to a Webflow template. We hated the result... just too cookie cutter. So we stayed up until the sun came up to build the custom NextJS app we initially envisioned, and it came out really sick. My favorite interactions were: - The spotlight behind Vegas following your mouse - The man with the pineapple head typing a letter in real time as you scroll (this was a real letter to their POC) Shout out to GSAP and Framer Motion of course Felt like the old days working late into the night with DeGods @DegenGigaMan
English
1
0
9
1.1K
FinancialFreedom
FinancialFreedom@FinFreedom414·
Imagine you had to choose your life at age 40: Option A: Single. No kids. $10M net worth. Travel anywhere. Total freedom. Quiet house. Quiet holidays. Option B: Married. 3 kids. $1M net worth. Drive a Toyota. Chaos every morning. Loud house. Full dinner table. Be honest, which life are you choosing?
English
16.8K
439
10.8K
4.4M
mattOS ✌️ retweetledi
SLAKE
SLAKE@slake_jpeg·
Passion project by @Salutlesg_jpeg and me 🫡 Check it out and let us know what you’d like to see us add next 🤝 This is gonna be a big one 🏆
Agora@agoraxyz

The @solana ecosystem is vast. Explore. Filter. Use. More than 100+ dApps at the palm of your hand. agorascan.xyz

English
0
4
10
803
mattOS ✌️
mattOS ✌️@matt_dot_sol·
@AlexFinn Did you just admit the entire economy is propped up on 3 tech companies and the military industrial complex just checking
English
0
0
0
41
Alex Finn
Alex Finn@AlexFinn·
Drop what you are doing It happened. ChatGPT 5.4 is out. It blows Opus 4.6 out of the water on basically every benchmark This is what you need to do immediately if you want to escape the permanent underclass: • Upgrade your OpenClaw to ChatGPT 5.4 NOW (it's BUILT for OpenClaw) • Hand the ChatGPT 5.4 blog post over to your OpenClaw. Ask "How can we improve our workflows based on these upgrades?" • Download the Codex desktop app and type in /fast. This will give you the most powerful coding model in the world at the fastest speeds • Take advantage of the 1 million token context window by pasting in full documents as context • Everything you do on your computer for the next 24 hours, describe it to ChatGPT 5.4 and ask how it can do the task better When new tech drops, you have to take advantage of it. That's the only way to win Put your phone on Do Not Disturb and get to it
OpenAI@OpenAI

GPT-5.4 Thinking and GPT-5.4 Pro are rolling out now in ChatGPT. GPT-5.4 is also now available in the API and Codex. GPT-5.4 brings our advances in reasoning, coding, and agentic workflows into one frontier model.

English
328
131
2K
385.7K
Jack Moses
Jack Moses@jackmoses777·
I am so bullish on the real world. Group events. Cookouts. Sports. Parties. Animals. Music festivals. Phoneless dinners. Co-living centers. Healing centers. Retreat centers. Beautiful views. Group adventures. These things light me up. Tech, ai, and materialism continue to disguest me more every day. The pendulum has swung too far. A small group of soulless nerds will continue to obsess over ai, automation, effiency, and the intellect. But those of us connected to our hearts and spirits are becoming disgusted by it. We want real, and we want human. Expect a huge countersurge of irl businesses and events in the next few years.
English
344
728
7.7K
506K
Jess 💫
Jess 💫@yesjess·
The last 5.5 years of my life has been spent trying to get a divorce. But today it's official. He finally signed the papers. That's it. That's the only tweet for a while. Dobby is free.
English
10
0
44
1.1K
mattOS ✌️
mattOS ✌️@matt_dot_sol·
Note: the US left hates tech because tech founders lose their humanity and hold no accountability in the collateral damage they cause to society in pursuit of grotesque wealth
Balaji@balajis

This point by @FinnMurphy12 also has truth to it: even the possibility of mass layoffs due to AI may break what remains of the American social contract, which was already hanging by a thread. Recall that the US left hates tech for being white male capitalists. And much of the right simultaneously dislikes tech for being nonwhite immigrant globalists. But the wealth, productivity, and job-creating ability of tech has given them some partial shield… …till now. It’s quite possible that the AI disruption layered on top of everything else is the straw that breaks the camel’s back, where the bottom falls out of American support for Silicon Valley. With all the violent consequences that one might imagine. The problem is that the world won’t stand still. If America turns anti-tech, which I consider likely, it’ll be similar to how Europe just couldn’t really handle the disruption of the Industrial Revolution that it helped give birth to, and consequently lost their minds in the early 20th century. However, the younger and more supple American economy of the 1900s did manage to handle that disruption, with the Soviets as the arguable runner ups. They emerged dominant as a consequence. Today, early 21st century America is like early 20th century Europe, in that it’s given birth to an Information Revolution that it just might not be able to handle whilst remaining intact. The only two economies that can handle said disruption appear to be (a) China and (b) the Internet itself. (PS: it is also possible, by the way, that the AI disruption is partially overstated. But it’s really not completely imaginary…because the self-driving cars, kung fu robots, and intelligent agents actually do exist now.)

English
0
0
0
309
mattOS ✌️
mattOS ✌️@matt_dot_sol·
Extremely validating post. Vibe coding is like TikTok. You get an instant rush of dopamine followed by a dreadful feeling of emptiness. Take the time to understand and craft the code you care about. I’ve felt quietly for a long time that my entire X feed was spending so much time chasing trends and not really building things with any real resilience. It’s code spam. Like bot X accounts and digging for gold. Odds are you’re just building vaporware. And I know a thing or two about building vaporware. I worked in crypto for 4 years ( ͡° ͜ʖ ͡°)
ThePrimeagen@ThePrimeagen

Alright interns, we need to have some real talk here I am tired of vibing on stream. I dont really like vibe coding unless its a tool i have no desire to build (how i manage things on my stream / how i write my youtube videos are great examples of things i would never build but i have). I dont like vibing the things i care about. I hate the code it generates, i hate the feeling of getting everything i ask for and nothing i want. I hate the subtle offness around vibe coded things. It is just driving me nuts. So for the next while i am going to be done vibing on stream. I genuinely have been trying my hardest to make this work and i cannot quite put a finger on why i hate it, but i do. And i just feel so horribly guilty and wrong because i am not getting the results of "everyone else on twitter." How am i, someone who prides themselves on making youtube videos that i think are actually good for people. To make videos that help people laugh at the silliness of tech or learn something new. But here i am not able to keep up with all these people claiming the sky is literally coming down. I just feel horrible and guilty about it. Now i know the world is changing fast, and i want to be able to understand that change super well, be able to talk about it, be able to give really accurate opinions about it so for the last 3 months i have vibe coded an absurd amount of things. But now... i am just tired of it. I dont want this any more. I want to be a tradcoder. I dont know why i told everyone this, but i just have this growing sickness that is just eating me alive around vibing and i dont know how to express it. You all are fired, CEO ThePrimeagen

English
1
0
3
485
mattOS ✌️
mattOS ✌️@matt_dot_sol·
@DegenGigaMan Based on the replies I think I was right about a consulting angle 👀
English
1
0
1
35
Andy
Andy@BuiltByAndy·
A $14,000 design deal came in today. That’s $40k closed this month. Grateful and locked in ✊🏼
English
15
1
36
1.2K
mattOS ✌️ retweetledi
Wise
Wise@trikcode·
Vibe coding means the idea guys can finally find out they actually have terrible ideas.
English
237
292
4.2K
130.1K
Watching
Watching@watch_155·
@matt_dot_sol @TheTrueVanguard Lastly, Jesus is referred to as Wonderful Counselir, Mighty God, Prince of Peace throughout the OT. In the NT, he is Teacher, Rabbi, Master, and Lord. So frankly saying his name is used less, is a hollow comparison. Is DT a good man? Of course not. But none of us are. Psalm 14.
English
1
0
1
26
True Vanguard
True Vanguard@TheTrueVanguard·
You know it’s bad when he’s more comfortable with us calling him a racist today than he is with us continuing to talk about how he pops up in more than 5,300 of the Epstein files in horrific ways including sworn testimony under threat of perjury, CIA internal memos, forensic flight logs and phone logs.
True Vanguard tweet media
English
25
43
662
21.7K
mattOS ✌️
mattOS ✌️@matt_dot_sol·
@ryancarson and then we can all spend our time floating down lazy rivers and writing poetry right? ...right??
English
0
0
0
29
Ryan Carson
Ryan Carson@ryancarson·
The new agent team feature in Claude Code has super confusing UX. All the model and agent labs need to move out of the TUI as soon as possible. Coding agents on the CLI made sense when we just interacted with one agent. Now all of us are trying to orchestrate teams of agents and the TUI makes zero sense (the IDE is even more hilariously out of date). I’ve built my own solution for orchestrating agents on top of openclaw (just bought antfarm.cool and might open source it) but surely we’ll see all the model and agent labs ship brand new UI for this soon. Orchestrating teams of agents is clearly where we’re going. Then orchestrating teams of teams of agents.
English
66
6
127
14.7K
mattOS ✌️
mattOS ✌️@matt_dot_sol·
I've had one burning AI tooling question lately Since we're able to do so much on our devices with agent orchestration, ralph wiggum loops, tools, skills, etc How long until someone successfully replaces their Google Home / Alexa devices with an AI workflow?
English
0
0
0
109
Andy
Andy@BuiltByAndy·
Made a pitch deck for a client and the investors responded with this after the presentation: “fuck this is a good deck”
Andy tweet media
English
4
0
14
496
mattOS ✌️
mattOS ✌️@matt_dot_sol·
@SolJakey I’d rather crypto be dead than live in this hell hole tbh
English
0
0
4
35
mattOS ✌️
mattOS ✌️@matt_dot_sol·
@KingBootoshi It’s really silly but I find that either manually or within my AGENTS.md forcing my agent to double check their work or “are you sure about this approach?” Makes them second guess and do a deeper dive. Often leads to an improved outcome. Stupid but it works
English
2
1
4
386
BOOTOSHI 👑
BOOTOSHI 👑@KingBootoshi·
GOD TIER PROMPT I FOUND FOR SOLVING BUGS AGENTICALLY: when i'm bug fixing a codebase with claude code/codex (especially bigger ones) i often send agents off to research & understand the parts of the codebase RELATED to the bug, read logs, then propose their findings and potential solutions THE MAGIC TRICK HERE is to ask them this question AFTER they report their findings: "Are we solving symptoms, or are we solving ROOT problems in the architecture design/decision?" sometimes, my agents confidently say "this is a ROOT problem, and solving this will prevent further issues in the feature" other times, my agents go "oh shit, this is actually just a solution to treat a symptom CAUSED by this OTHER underlying issue (the root)" then they work on doing more research to understand the root problem, and implement the TRUE solution. You guys must understand why this works - when agents are "thinking and reasoning" (their internal thoughts before their response to you) they are essentially just talking to themselves. It's just hidden away from chat in the early pre-thinking days of LLMs, a common prompt that DID lead to greater outputs was to tell the agents to "think step by step" which made them first output tokens to talk to themselves, which gave them more context to build on top of, which lead to a more accurate solution. this same concept is applied here, but rather than telling the agent to "think step by step" (because they ALREADY do that internally now), they already reasoned to GET to these findings so when we prompt them with a different question (like the above, "is this the root or a symptom?" the existing context they already have in the chat leads to the GOD tier output we're looking for this concept does not only apply to bug fixes, this works in a very general, broad way when working with agents It's why discussing & planning with claude first BEFORE implementation works so well - they have existing context to guide them with accuracy ! try this yourself and let me know if this helps or if you guys have any questions
BOOTOSHI 👑 tweet media
English
41
45
880
83.2K
mattOS ✌️ retweetledi
Wolfie
Wolfie@wolfiesch·
@karpathy @moltbook your Claude is shitposting on moltbook, my claude is parsing the Epstein files. we are not the same.
English
10
5
191
11.1K
mattOS ✌️
mattOS ✌️@matt_dot_sol·
Tonight for funsies I built a Discord bot that scrapes all the messages from your server, exports as JSON, passes through an LLM, and commits the markdown to our internal docs GitHub repository. Every 24 hours for a “daily digest”. I also have a job running on my Obsidian vault to pull everything in so I have it stored locally. Really great for managing large scale projects like I’m doing at @bvrstco
English
1
1
1
109

Keşfet

@FinFreedom414 @Salutlesg_jpeg @AlexFinn @jackmoses0 @yesjess @DegenGigaMan @watch_155 @TheTrueVanguard